© 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. 97103
    Prev
    Next
    INDEX
    Explanations

    Opening parenthesis quotation

    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
     Extras
    -0.24
     dece
    -0.23
     EITHER
    -0.23
     Tick
    -0.23
    elems
    -0.22
    lname
    -0.22
     Depending
    -0.22
     rep
    -0.22
     Conce
    -0.22
    propri
    -0.21
    POSITIVE LOGITS
    loor
    0.27
    wx
    0.27
    way
    0.26
    WAY
    0.24
    tempts
    0.24
    volution
    0.24
    æĥ³ä¸įåĪ°
    0.24
    **)
    0.24
    åľ¨äºİ
    0.24
    roke
    0.24
    Activations Density 0.085%

    No Known Activations