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. 46442
    Prev
    Next
    INDEX
    Explanations

    programming and solutions

    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
    cat
    -0.29
    infinity
    -0.26
    ìĬ¤íĥĢ
    -0.26
    ingroup
    -0.26
    abis
    -0.26
    config
    -0.25
    .Ar
    -0.25
    欢è¿İæĤ¨
    -0.25
    	cat
    -0.25
     Abram
    -0.25
    POSITIVE LOGITS
    /raw
    0.27
    .Toggle
    0.26
     моменÑĤ
    0.25
    enas
    0.25
    éĨĴ
    0.24
    uxtap
    0.24
     commissions
    0.24
    ħ§
    0.23
     turnovers
    0.23
    achts
    0.23
    Activations Density 0.002%

    No Known Activations