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. 53695
    Prev
    Next
    INDEX
    Explanations

    negation

    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
    ampp
    -0.26
       
    -0.26
    ÑĢан
    -0.25
     sense
    -0.24
    褥
    -0.24
     dough
    -0.24
     Gam
    -0.24
     exact
    -0.24
     exercise
    -0.23
    纳æĸ¯
    -0.23
    POSITIVE LOGITS
    ç¬ij容
    0.27
     textColor
    0.25
    æĻ¯
    0.25
    elong
    0.24
    <g
    0.24
     pleasures
    0.24
     shale
    0.24
    æı©
    0.24
    (pf
    0.23
    imentary
    0.23
    Activations Density 0.812%

    No Known Activations