© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88743
    Prev
    Next
    INDEX
    Explanations

    stroke

    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
    Negative Logits
    çľĭä»ĸ
    -0.29
    çľ¼çľĭ
    -0.26
    arpa
    -0.26
    assemble
    -0.25
    /interfaces
    -0.24
    ਮ
    -0.24
    éĥ½æľīçĿĢ
    -0.24
    ç³ľ
    -0.24
    fdf
    -0.24
    .deserialize
    -0.23
    POSITIVE LOGITS
    ives
    0.31
    ä½ĵéªĮ
    0.27
    .ev
    0.26
     side
    0.25
    èī¯
    0.25
     immediate
    0.25
    walls
    0.24
     sides
    0.23
    ibles
    0.23
    #c
    0.23
    Activations Density 0.011%

    No Known Activations