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. 46076
    Prev
    Next
    INDEX
    Explanations

    women

    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
    平衡
    -0.32
    anja
    -0.28
    ä¼łç»Ł
    -0.28
     balanced
    -0.28
     traditional
    -0.27
    çļĦä¼łç»Ł
    -0.27
    è¡¡
    -0.26
    Traditional
    -0.26
    SCRI
    -0.25
    uese
    -0.25
    POSITIVE LOGITS
     arrives
    0.30
     arriving
    0.28
     poj
    0.28
    sembl
    0.26
     Climate
    0.26
    ä¸Ńè¶ħ
    0.25
     Arrival
    0.25
     Taxi
    0.25
     ventured
    0.24
     trump
    0.24
    Activations Density 0.013%

    No Known Activations