© 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. 35-TRANSCODER-HP
    7. 40413
    Prev
    Next
    INDEX
    Explanations

    silicon/silencing/silkmoth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paginate
    -0.31
     doll
    -0.26
     вал
    -0.25
    éī´åĪ«
    -0.25
     tact
    -0.25
     pest
    -0.25
     BEST
    -0.24
    tent
    -0.24
    dent
    -0.24
    bero
    -0.23
    POSITIVE LOGITS
    sky
    0.33
     sky
    0.30
     moreover
    0.28
    owy
    0.28
    omal
    0.28
    fulness
    0.28
    Sky
    0.28
    kre
    0.27
     furthermore
    0.26
     significance
    0.25
    Activations Density 2.817%

    No Known Activations