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. 54550
    Prev
    Next
    INDEX
    Explanations

    Code/markup snippets

    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
    æľºåĬ¨
    -0.28
    inker
    -0.28
     acompan
    -0.27
    ué
    -0.27
    isas
    -0.26
     followed
    -0.26
    å¼ºåĽ½
    -0.25
     Kern
    -0.25
    adic
    -0.25
    æĴ®
    -0.24
    POSITIVE LOGITS
    illions
    0.27
    OTT
    0.27
     tits
    0.25
    OMB
    0.25
     sounding
    0.25
    æİ¥ç®¡
    0.24
    æĪ·
    0.24
     vá»įng
    0.24
    ób
    0.24
    çļĦåľ°åĽ¾
    0.24
    Activations Density 0.821%

    No Known Activations