© 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. 38563
    Prev
    Next
    INDEX
    Explanations

    bi

    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
    Negative Logits
     t
    -0.29
    geh
    -0.29
    arse
    -0.29
    as
    -0.27
     a
    -0.26
    iro
    -0.26
    Ñĩе
    -0.26
    stor
    -0.26
     vt
    -0.25
    arro
    -0.25
    POSITIVE LOGITS
     Bulldogs
    0.28
    åħ¬å¼ĢèµĽ
    0.27
    ub
    0.26
     cannabin
    0.26
    OMATIC
    0.26
    ab
    0.25
    abol
    0.25
    annabin
    0.24
    ob
    0.24
     GBP
    0.24
    Activations Density 2.421%

    No Known Activations