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. 53782
    Prev
    Next
    INDEX
    Explanations

    code/URL structure

    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
    eti
    -0.35
    escal
    -0.27
    setId
    -0.27
    .TO
    -0.27
     Gian
    -0.26
    yı
    -0.26
     dealings
    -0.26
    ilda
    -0.25
     crawling
    -0.24
     intellig
    -0.24
    POSITIVE LOGITS
    追æ±Ĥ
    0.28
    让æĤ¨
    0.27
    moz
    0.27
    让
    0.26
    rench
    0.26
    feedback
    0.26
    lot
    0.25
    áºŃn
    0.25
    вÑĭ
    0.25
    çľŁç©º
    0.25
    Activations Density 0.213%

    No Known Activations