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. 1720
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    -caret
    -0.29
    éĨª
    -0.28
    åĵªæĢķæĺ¯
    -0.27
     hurting
    -0.26
    kaar
    -0.26
    éŀŃ
    -0.25
    åĵªæĢķ
    -0.25
    ноп
    -0.24
    edith
    -0.24
    积æŀģéħįåIJĪ
    -0.24
    POSITIVE LOGITS
    igh
    0.26
    åŃº
    0.25
    anced
    0.25
    ç«ĭæ³ķ
    0.24
    èĤ¡
    0.24
    产çĶŁ
    0.24
     distinct
    0.24
    âŁ¹
    0.23
    æ²½
    0.23
     difficolt
    0.23
    Activations Density 0.002%

    No Known Activations