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. 53909
    Prev
    Next
    INDEX
    Explanations

    experience

    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
    icont
    -0.27
    ponsored
    -0.27
    æī®
    -0.26
    ystack
    -0.25
     emulate
    -0.25
    fen
    -0.25
     strip
    -0.24
    buch
    -0.24
     supern
    -0.24
     EXPER
    -0.24
    POSITIVE LOGITS
    人å¿ĥ
    0.30
    çķ¿
    0.28
    æĪIJ为ä¸Ģ个
    0.28
    ine
    0.27
    Optimizer
    0.26
     AVC
    0.26
    metrical
    0.26
    rice
    0.26
    ç¾İçļĦ
    0.25
    ç¾İæĦŁ
    0.25
    Activations Density 0.066%

    No Known Activations