© 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. 96832
    Prev
    Next
    INDEX
    Explanations

    asterisk symbol

    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
    Not in Any Lists

    No Comments

    Negative Logits
    kim
    -0.32
    &E
    -0.30
    çħŀ
    -0.29
     Autor
    -0.27
    åĶĽ
    -0.26
     author
    -0.26
     autocomplete
    -0.26
     autor
    -0.25
     Aut
    -0.25
    æĭ¿æĿ¥
    -0.25
    POSITIVE LOGITS
    oppers
    0.29
    ä¹Ĥ
    0.26
    jective
    0.25
    chedulers
    0.24
    Jos
    0.24
     spot
    0.24
    åijµ
    0.24
    ihad
    0.24
    úb
    0.24
    -over
    0.24
    Activations Density 0.102%

    No Known Activations