© 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. 97896
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    à´±
    -0.27
    _>
    -0.24
     softened
    -0.23
    éŀĺ
    -0.23
    ëį°
    -0.23
    &E
    -0.23
    bö
    -0.23
    wä
    -0.23
    访è°Ī
    -0.22
    ÑĢенд
    -0.22
    POSITIVE LOGITS
    éĥ½è¢«
    0.26
     viol
    0.26
    opr
    0.25
    ç»ıå¼Ģ
    0.24
    viol
    0.24
     connects
    0.23
    WN
    0.23
     keyst
    0.22
     J
    0.22
    åıªä¸įè¿ĩ
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.