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. 53870
    Prev
    Next
    INDEX
    Explanations

    crime

    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
     Pros
    -0.28
     "~/
    -0.26
    pcb
    -0.26
    vara
    -0.26
    ugged
    -0.26
     Hom
    -0.25
    éĻĤ
    -0.24
    交ç»Ļ
    -0.24
    éŨæĪ·
    -0.24
    _hom
    -0.24
    POSITIVE LOGITS
    ko
    0.27
    åŃij
    0.26
     annex
    0.25
    ak
    0.24
    lo
    0.24
    Scrollbar
    0.23
     numer
    0.23
     ko
    0.23
    apyrus
    0.23
     matplotlib
    0.23
    Activations Density 0.028%

    No Known Activations