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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77196
    Prev
    Next
    INDEX
    Explanations

    requests or confirmations about rewriting text into a more elegant, high-register (literary) style.

    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
    .jet
    -0.08
    悪
    -0.07
    面包
    -0.07
     म
    -0.07
     STD
    -0.07
    )],
    -0.07
     控
    -0.07
    -inf
    -0.07
     propositions
    -0.06
     psychiat
    -0.06
    POSITIVE LOGITS
     Till
    0.07
     Lum
    0.07
     PEN
    0.07
    过关
    0.07
     Publisher
    0.07
    排除
    0.07
     lumière
    0.07
    市场
    0.06
    erved
    0.06
     readily
    0.06
    Activations Density 0.112%

    No Known Activations