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. 46768
    Prev
    Next
    INDEX
    Explanations

    colons

    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
    ä¸¤å¼ł
    -0.28
    long
    -0.27
    éķ¿æĹ¶éĹ´
    -0.27
    éķ¿
    -0.26
    voy
    -0.26
    Ty
    -0.25
    ridor
    -0.25
     diffé
    -0.24
    ey
    -0.24
    suma
    -0.24
    POSITIVE LOGITS
    "class
    0.35
    æ²Ķ
    0.27
     ERC
    0.27
     fiberglass
    0.26
    IOUS
    0.25
    âĸ·
    0.24
    fds
    0.24
     Bingo
    0.24
    SEL
    0.24
     bree
    0.24
    Activations Density 0.019%

    No Known Activations