© 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. 87195
    Prev
    Next
    INDEX
    Explanations

    events

    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
    lip
    -0.28
    arro
    -0.27
    stitutions
    -0.25
    èĭ¥æľī
    -0.25
    åı¤åŁİ
    -0.25
    çĶŁæ´»çļĦ
    -0.25
    areth
    -0.24
    throp
    -0.24
     uniquely
    -0.24
     submodule
    -0.24
    POSITIVE LOGITS
    REST
    0.27
    è·ij
    0.27
    _BACKEND
    0.27
    è¯Ħä»·
    0.26
    IX
    0.24
     Som
    0.24
    à¸Ĺราà¸ļ
    0.24
    è¿ĽèĢĮ
    0.24
    ion
    0.24
    vang
    0.24
    Activations Density 0.008%

    No Known Activations