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. 53313
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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
     unic
    -0.26
    礼è²Į
    -0.25
     stumbled
    -0.25
    initely
    -0.25
    ritt
    -0.25
     tied
    -0.25
    onation
    -0.24
    ruption
    -0.24
     Herald
    -0.23
    ä¸Ģäºĭ
    -0.23
    POSITIVE LOGITS
    оÑī
    0.27
    LLL
    0.26
    ielding
    0.25
    ảnh
    0.25
    åī¯ä¸»å¸Ń
    0.24
    czÄħ
    0.24
    '):↵
    0.24
     customary
    0.24
    æł·çļĦ
    0.24
    ANI
    0.24
    Activations Density 0.024%

    No Known Activations