© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129830
    Prev
    Next
    INDEX
    Explanations

    Correlation and relations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gấp
    -0.28
    lining
    -0.26
    lections
    -0.25
    uko
    -0.25
    liner
    -0.25
    ergy
    -0.25
    ahead
    -0.24
    å°Ĩè¿İæĿ¥
    -0.24
    rush
    -0.24
    ingham
    -0.24
    POSITIVE LOGITS
    串
    0.29
    Gatt
    0.29
    inus
    0.26
    åĽłæŀľ
    0.25
     disorder
    0.25
     Cool
    0.23
     lat
    0.23
    klä
    0.23
     texting
    0.22
     between
    0.22
    Activations Density 0.017%

    No Known Activations