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. 54565
    Prev
    Next
    INDEX
    Explanations

    queen

    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
    èѦæĥķ
    -0.29
    åŀĴ
    -0.27
    海绵
    -0.27
    娶
    -0.26
     pró
    -0.25
    оÑĢо
    -0.25
    stock
    -0.25
    autos
    -0.25
     Jelly
    -0.25
    yun
    -0.24
    POSITIVE LOGITS
    omic
    0.29
    ippi
    0.27
    lip
    0.27
    æľĪä¸ĭ
    0.26
    æľĪ
    0.25
    人ãģ¯
    0.25
    _ABI
    0.24
    lights
    0.24
    ights
    0.24
    èĸģ
    0.24
    Activations Density 1.737%

    No Known Activations