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

    Neuronpedia

    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. 77549
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    (interp
    -0.08
     Sebastian
    -0.07
     mainAxisAlignment
    -0.07
    <Value
    -0.07
    .mixer
    -0.07
    jective
    -0.07
     Second
    -0.07
    <KeyValuePair
    -0.07
     constexpr
    -0.07
     Crossing
    -0.07
    POSITIVE LOGITS
    six
    0.08
     Identity
    0.07
    라
    0.07
    形成的
    0.07
    /files
    0.07
     enlightened
    0.07
    !='
    0.07
    看到了
    0.07
    藏
    0.07
    看
    0.07
    Activations Density 0.013%

    No Known Activations