© 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. 9-TRANSCODER-HP
    7. 30188
    Prev
    Next
    INDEX
    Explanations

    agoon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otel
    -0.27
    -focused
    -0.26
    éĥ½åĸľæ¬¢
    -0.26
    欧å¼ı
    -0.26
    ottom
    -0.25
    ransition
    -0.24
    大è¡Ĺ
    -0.24
    ием
    -0.24
    说èĩªå·±
    -0.24
    æıIJæ¡Ī
    -0.24
    POSITIVE LOGITS
    èµĽåIJİ
    0.28
    uch
    0.27
    .RequestBody
    0.26
     posto
    0.26
    æ¯į
    0.26
     sond
    0.26
    uchs
    0.25
    æ¯į亲
    0.25
    çĶ³
    0.25
    質
    0.25
    Activations Density 3.215%

    No Known Activations