© 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. 88207
    Prev
    Next
    INDEX
    Explanations

    just

    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
    çĶļèĩ³
    -0.30
    дон
    -0.28
     neighbouring
    -0.26
    éĻĦè¿ij
    -0.26
    ä»»ä½ķ人
    -0.26
    çĶļèĩ³æĺ¯
    -0.25
    reh
    -0.25
    -fontawesome
    -0.25
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.25
    rev
    -0.24
    POSITIVE LOGITS
    ather
    0.29
    mpp
    0.27
    ldb
    0.26
    .$.
    0.26
    leck
    0.25
     uphill
    0.25
     Kapoor
    0.25
    ensch
    0.24
    uest
    0.24
     Serbian
    0.24
    Activations Density 0.012%

    No Known Activations