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. 54589
    Prev
    Next
    INDEX
    Explanations

    varied contexts

    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
     supply
    -0.27
    è¿Ľç¨ĭ
    -0.26
    intage
    -0.26
    èĵĿ
    -0.26
    æīĢè°ĵ
    -0.26
     Fly
    -0.26
    unte
    -0.25
     Supply
    -0.25
    åݨå¸Ī
    -0.24
     tá»
    -0.24
    POSITIVE LOGITS
    ãĥĥãĤ¯
    0.28
     Gutenberg
    0.26
    Exam
    0.25
    ×ķ×ĵ×ķת
    0.25
    omic
    0.24
    åħ¨åľĭ
    0.24
    eneg
    0.24
     nationwide
    0.24
    çļĦåľŁåľ°
    0.24
    enheim
    0.24
    Activations Density 0.026%

    No Known Activations