© 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. 8736
    Prev
    Next
    INDEX
    Explanations

    giving instructions

    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
     getS
    -0.07
    (xx
    -0.07
    时代的
    -0.06
     Leo
    -0.06
    &p
    -0.06
    Portrait
    -0.06
     Od
    -0.06
     Boxes
    -0.06
    isor
    -0.06
     texts
    -0.06
    POSITIVE LOGITS
    .float
    0.07
    there
    0.07
    _makeConstraints
    0.07
    僳
    0.07
    /ubuntu
    0.07
    🅶
    0.07
     Abdul
    0.07
     distinguishing
    0.07
    pring
    0.07
     --
    0.06
    Activations Density 0.120%

    No Known Activations