© 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. 31-TRANSCODER-HP
    7. 18087
    Prev
    Next
    INDEX
    Explanations

    Book excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èmes
    -0.27
    icho
    -0.27
     ceil
    -0.26
    elenium
    -0.26
    .poly
    -0.25
    ï¼ĺ
    -0.25
    é£İæ°´
    -0.24
    åħ«åŃĹ
    -0.24
     Nairobi
    -0.24
    leep
    -0.23
    POSITIVE LOGITS
    atin
    0.31
    oder
    0.29
     maint
    0.28
    åľ¨çİ°åľº
    0.27
    ÙĪا
    0.26
    gment
    0.26
    اة
    0.26
    ÑĪей
    0.25
    utt
    0.25
     maintain
    0.25
    Activations Density 13.226%

    No Known Activations