© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 89550
    Prev
    Next
    INDEX
    Explanations

    urities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rchive
    -0.07
    飨
    -0.07
    졪
    -0.06
     MacOS
    -0.06
     bed
    -0.06
     GUIStyle
    -0.06
    湾
    -0.06
    窝
    -0.06
    ➧
    -0.06
     Chapel
    -0.06
    POSITIVE LOGITS
     shadow
    0.08
     aggregates
    0.07
     atrocities
    0.07
     artificially
    0.07
     conj
    0.07
    /issues
    0.06
     markers
    0.06
     superiority
    0.06
    有限
    0.06
     collections
    0.06
    Activations Density 0.009%

    No Known Activations