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. 146679
    Prev
    Next
    INDEX
    Explanations

    cause

    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
    ches
    -0.27
    auge
    -0.27
    rlen
    -0.26
    å¹£
    -0.26
    vider
    -0.26
    alis
    -0.26
    .Resolve
    -0.25
    çĤ¬
    -0.25
    panse
    -0.25
    łģ
    -0.25
    POSITIVE LOGITS
    tg
    0.27
    elite
    0.27
    æłijæŀĹ
    0.26
     Indo
    0.26
    IRD
    0.26
    phin
    0.25
    ç»ıèIJ¥æ´»åĬ¨
    0.25
     tease
    0.25
    æ°¸è¿ľ
    0.24
    年轻人
    0.24
    Activations Density 0.023%

    No Known Activations