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. 54538
    Prev
    Next
    INDEX
    Explanations

    formal descriptions

    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
     rented
    -0.28
    软
    -0.27
    è¡Į为
    -0.25
    ollar
    -0.24
    ë°ķ
    -0.24
    éĤ»
    -0.24
    ç§Ł
    -0.24
     ÑģÑĤÑĥд
    -0.24
    .TextField
    -0.23
    ot
    -0.23
    POSITIVE LOGITS
     celib
    0.26
    aims
    0.25
    éĩı产
    0.25
     thinker
    0.24
     promot
    0.24
    icie
    0.24
    atonin
    0.23
    _namespace
    0.23
    çαç¾İ
    0.23
    stamp
    0.23
    Activations Density 0.013%

    No Known Activations