© 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. 130454
    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
    åħĪæĺ¯
    -0.24
    iren
    -0.22
    ilage
    -0.22
    èĢĨ
    -0.22
     meal
    -0.22
    !--
    -0.22
    eting
    -0.21
    latin
    -0.21
    åĽ½ç«ĭ
    -0.21
    remely
    -0.20
    POSITIVE LOGITS
    å¼¼
    0.30
    å¼¥
    0.23
    æ¢Ĩ
    0.22
    éĻIJãĤĬ
    0.22
    _ATTR
    0.21
    itution
    0.21
     Blake
    0.21
    ulp
    0.21
    breadcrumb
    0.20
    alent
    0.20
    Activations Density 0.081%

    No Known Activations

    This feature has no known activations.