© 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. 33-TRANSCODER-HP
    7. 52693
    Prev
    Next
    INDEX
    Explanations

    laws and official documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ver
    -0.28
    VER
    -0.27
    ç»´
    -0.27
    ion
    -0.27
    ewolf
    -0.25
    æĺ¯åľ¨
    -0.25
    Ver
    -0.25
    ç³Ł
    -0.25
    æĭī
    -0.25
    饿
    -0.25
    POSITIVE LOGITS
    åħ¬å®īéĥ¨
    0.26
     Guys
    0.25
     Grades
    0.24
    rats
    0.23
    _TYPES
    0.23
     Days
    0.23
    tps
    0.23
     Mand
    0.23
    stantiate
    0.23
     typingsJapgolly
    0.23
    Activations Density 0.009%

    No Known Activations