© 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. 30-TRANSCODER-HP
    7. 97122
    Prev
    Next
    INDEX
    Explanations

    collaboration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¡Įãģį
    -0.27
     cracked
    -0.27
     Sass
    -0.27
    çªģåĽ´
    -0.27
     tweeted
    -0.26
    è°İ
    -0.26
    çŁ¥éģĵèĩªå·±
    -0.26
    .rs
    -0.25
     matter
    -0.24
     fetched
    -0.24
    POSITIVE LOGITS
     collaborating
    0.34
     collaboration
    0.34
    主ä¸ļ
    0.34
    coll
    0.34
     conducts
    0.33
     conducted
    0.33
     conducting
    0.33
     cooper
    0.33
     cooperative
    0.33
     collaborate
    0.32
    Activations Density 0.889%

    No Known Activations