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. 47431
    Prev
    Next
    INDEX
    Explanations

    Aviation

    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
    önü
    -0.35
    çĥĿ
    -0.28
    reh
    -0.25
     trì
    -0.25
     ieee
    -0.24
     Blink
    -0.24
    .inst
    -0.24
    éĢģæĿ¥
    -0.23
    ukt
    -0.23
     Conditional
    -0.23
    POSITIVE LOGITS
    lectic
    0.29
    åıł
    0.28
    ç»Į
    0.27
    appa
    0.26
     Acad
    0.25
    win
    0.25
    bot
    0.24
    unique
    0.24
    寡
    0.24
    èķ¾
    0.24
    Activations Density 0.019%

    No Known Activations