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. 53854
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
    åºŁæ°´
    -0.28
    logen
    -0.27
     announce
    -0.26
    头
    -0.26
    _family
    -0.25
    ú
    -0.25
    urple
    -0.25
     mix
    -0.25
    ÿ
    -0.25
    qs
    -0.24
    POSITIVE LOGITS
    ANTI
    0.33
    æij©æīĺ
    0.29
    :create
    0.26
    俯
    0.26
    ANTA
    0.25
    ANGO
    0.25
     feathers
    0.25
     Griff
    0.24
    anst
    0.24
    .wind
    0.24
    Activations Density 0.020%

    No Known Activations