© 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. 97429
    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
    缴è§Ĥ
    -0.25
    erd
    -0.25
    票
    -0.24
    emark
    -0.24
     Adult
    -0.24
     flash
    -0.24
     illumination
    -0.23
    æŶæĬ¥
    -0.23
    Nguá»ĵn
    -0.23
    ishi
    -0.23
    POSITIVE LOGITS
    bia
    0.27
    Draft
    0.26
    ankan
    0.26
     Draft
    0.25
    umping
    0.25
    顺
    0.25
    anken
    0.24
    ä¿ħ
    0.24
    umped
    0.24
    lias
    0.23
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.