© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 74108
    Prev
    Next
    INDEX
    Explanations

    tokens with unconventional capitalization patterns, such as internal capitals, capitals immediately after hyphens, or capital-letter/digit acronyms, often in proper names and abbreviations.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存款
    -0.08
    omain
    -0.08
    ⊨
    -0.07
     rel
    -0.07
    ｂ
    -0.07
    \<
    -0.07
    })↵↵↵
    -0.07
    ولد
    -0.07
    \\\
    -0.07
     małe
    -0.07
    POSITIVE LOGITS
     Goes
    0.08
    最近
    0.07
     Huckabee
    0.07
     esports
    0.07
    厝
    0.07
     EAST
    0.07
    畔
    0.07
     Pompeo
    0.07
     sürekli
    0.07
    noopener
    0.07
    Activations Density 0.464%

    No Known Activations