© 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. 129280
    Prev
    Next
    INDEX
    Explanations

    that

    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
    å¦Ĥæŀľè¯´
    -0.36
    æłĩçļĦ
    -0.26
    AFE
    -0.26
    æľ¬è½®
    -0.26
     Banc
    -0.26
    为ä»Ģä¹Īè¦ģ
    -0.25
     karÅŁ
    -0.25
     There
    -0.25
    oze
    -0.24
    å¦Ĥæŀľæĺ¯
    -0.24
    POSITIVE LOGITS
    缸åħ³æĸ°éĹ»
    0.27
    //=
    0.26
     sez
    0.26
    weigh
    0.25
    tfoot
    0.25
     LIABILITY
    0.25
    nofollow
    0.25
    contrib
    0.24
    bd
    0.24
    HttpPost
    0.24
    Activations Density 0.004%

    No Known Activations