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. 54533
    Prev
    Next
    INDEX
    Explanations

    =

    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
    ä¼ł
    -0.32
    ä¼ĺåħĪ
    -0.28
    .Global
    -0.27
    欢è¿İ大家
    -0.26
    ust
    -0.26
     ct
    -0.25
     ot
    -0.25
    =find
    -0.24
     ourselves
    -0.24
    usta
    -0.24
    POSITIVE LOGITS
    èĿ°
    0.28
    chner
    0.27
    ereco
    0.27
    ç®±åŃIJ
    0.26
     liter
    0.26
    -controlled
    0.25
    ÃľN
    0.25
    oles
    0.24
    èĪŀåı°ä¸Ĭ
    0.24
    olf
    0.24
    Activations Density 0.001%

    No Known Activations