© 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. 112342
    Prev
    Next
    INDEX
    Explanations

    /

    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
    é
    -0.24
    è®®
    -0.24
     enabled
    -0.24
    çı¥
    -0.24
     paint
    -0.23
    hdl
    -0.23
    sheets
    -0.23
    éģ©åIJĪ
    -0.23
     burn
    -0.23
     altogether
    -0.22
    POSITIVE LOGITS
    ssp
    0.26
    oland
    0.25
     Tmin
    0.25
    getVar
    0.25
    oure
    0.24
    VIP
    0.24
     yyn
    0.24
    verter
    0.24
     Tmax
    0.23
     mip
    0.23
    Activations Density 0.007%

    No Known Activations