© 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. 97050
    Prev
    Next
    INDEX
    Explanations

    food recipes

    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
    ót
    -0.27
    ä»ĩ
    -0.27
    adal
    -0.27
    agos
    -0.26
    ROC
    -0.26
     ROC
    -0.26
    à¹Į
    -0.26
    PEG
    -0.26
     imperative
    -0.25
    ACP
    -0.24
    POSITIVE LOGITS
    ground
    0.26
    ç¨İåĬ¡æĢ»å±Ģ
    0.25
    fleet
    0.24
     Moms
    0.24
    ivre
    0.24
    rypted
    0.24
    silver
    0.24
    delegate
    0.24
     Mods
    0.24
    RAL
    0.23
    Activations Density 0.886%

    No Known Activations