Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 46599
    Prev
    Next
    INDEX
    Explanations

    DNA methylation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Decl
    -0.30
    Decl
    -0.28
     gre
    -0.27
    _decl
    -0.26
    æĹı群
    -0.26
     GC
    -0.25
    --*/↵
    -0.25
    ****************************************************************************
    -0.25
    emachine
    -0.25
     manual
    -0.25
    POSITIVE LOGITS
    TRA
    0.27
    gun
    0.27
    éĮ¯
    0.25
     één
    0.25
    Ñĥг
    0.25
    elda
    0.25
     Inspection
    0.24
    uro
    0.24
    sbin
    0.24
    peon
    0.24
    Activations Density 0.010%

    No Known Activations