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. 146602
    Prev
    Next
    INDEX
    Explanations

    ectomy

    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
    ä»ĸçŁ¥éģĵ
    -0.25
    ç§ĺ
    -0.24
    粤
    -0.24
     recycle
    -0.24
     recycled
    -0.24
     LG
    -0.24
     highest
    -0.24
    åĬ©çIJĨ
    -0.24
    endif
    -0.23
    pitch
    -0.23
    POSITIVE LOGITS
    maf
    0.27
    åĽ´çĿĢ
    0.27
    èĽŁ
    0.26
    onom
    0.26
    æİª
    0.25
    åĽ´
    0.25
    æĪĺçķ¥å¸ĥå±Ģ
    0.25
    ropol
    0.25
    对åħ¬åı¸
    0.24
     Banana
    0.23
    Activations Density 0.038%

    No Known Activations