© 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. 87087
    Prev
    Next
    INDEX
    Explanations

    informed

    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
    ãģ¾ãĤĮ
    -0.28
     hatch
    -0.25
    archives
    -0.24
    æĻ®éĢļè¯Ŀ
    -0.24
    ä¸Ģ件äºĭæĥħ
    -0.23
    SCII
    -0.23
    Americ
    -0.23
    ued
    -0.23
    andal
    -0.23
    iele
    -0.23
    POSITIVE LOGITS
    à¤ĸ
    0.27
    utive
    0.26
    .requireNonNull
    0.25
    å±Ī
    0.24
    osc
    0.24
    ixo
    0.23
    itore
    0.23
    à¦ĸ
    0.23
    èĩªæĦ¿
    0.23
    ç¨ĭ度
    0.23
    Activations Density 0.076%

    No Known Activations