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. 7-TRANSCODER-HP
    4. 24690
    Prev
    Next
    INDEX
    Explanations

    visual detection/blind spots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uncont
    -0.28
    æļij
    -0.26
    æĮģ
    -0.24
    ä»¶
    -0.24
     super
    -0.24
    转åħ¥
    -0.24
    éĢļ
    -0.23
    ients
    -0.23
    --↵↵
    -0.23
    felt
    -0.23
    POSITIVE LOGITS
    ç¼
    0.28
    çļĦåħ´è¶£
    0.26
    _integer
    0.26
     bef
    0.26
    æīĭæİĮ
    0.25
    iosis
    0.25
    åħ´è¶£
    0.25
    bru
    0.25
    æĮ¹
    0.25
    说æĺİ
    0.24
    Activations Density 0.001%

    No Known Activations