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. 7-TRANSCODER-HP
    4. 130254
    Prev
    Next
    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uden
    -0.29
    æī°
    -0.29
    ANN
    -0.25
     ServiceProvider
    -0.25
    Ãło
    -0.24
    åĨ°éĽª
    -0.24
    lo
    -0.24
    anne
    -0.24
    ŀ
    -0.24
    師
    -0.23
    POSITIVE LOGITS
    åľºæĻ¯
    0.27
    cake
    0.27
    Brush
    0.26
    ä¸įèĥ½åĨį
    0.26
     Brush
    0.25
    eton
    0.25
     antlr
    0.25
     Reality
    0.24
    åѱ
    0.24
    /MIT
    0.24
    Activations Density 0.001%

    No Known Activations