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. 53210
    Prev
    Next
    INDEX
    Explanations

    stimulated

    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
    emens
    -0.28
    łģ
    -0.28
    cene
    -0.27
     Communic
    -0.27
    ôme
    -0.27
    gos
    -0.26
     sac
    -0.25
    opsy
    -0.25
    Ñģло
    -0.24
    unts
    -0.24
    POSITIVE LOGITS
     manifest
    0.27
    3
    0.27
    表çݰ
    0.27
    以åIJİ
    0.27
    8
    0.26
    çļĦåıijå±ķ
    0.26
    a
    0.25
     manifestation
    0.24
    æĹ©åľ¨
    0.24
    ëĭĪëĭ¤
    0.24
    Activations Density 0.002%

    No Known Activations