© 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. 97951
    Prev
    Next
    INDEX
    Explanations

    Code/symbols

    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
    stalk
    -0.26
     Renders
    -0.26
    bands
    -0.24
    icolon
    -0.24
    band
    -0.24
    tempts
    -0.24
    .indexOf
    -0.23
    _band
    -0.23
    panse
    -0.23
    éĸ¢ãĤı
    -0.23
    POSITIVE LOGITS
     sub
    0.28
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.28
    ccd
    0.27
     ed
    0.27
     sn
    0.25
    ABL
    0.24
    vel
    0.24
    aN
    0.24
    ↵↵↵↵↵↵↵↵
    0.24
     tor
    0.24
    Activations Density 0.010%

    No Known Activations