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. 47468
    Prev
    Next
    INDEX
    Explanations

    technical/computer text

    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
    æĹ¢
    -0.30
    ovan
    -0.28
    çĭ¬
    -0.27
    ovation
    -0.26
    -break
    -0.26
    ÙĬدة
    -0.25
    abilidade
    -0.24
    交ä»ĺ
    -0.24
     filament
    -0.24
    ç»Ŀç¼ĺ
    -0.24
    POSITIVE LOGITS
     soak
    0.26
     forgiven
    0.25
    .defaults
    0.25
    çĻĶ
    0.25
     probing
    0.24
     yaptıģı
    0.24
    澡
    0.23
     Initializing
    0.23
    âĿ¥
    0.23
     LOC
    0.23
    Activations Density 0.027%

    No Known Activations