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. 97716
    Prev
    Next
    INDEX
    Explanations

    gallery

    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
    shall
    -0.36
    ä¾
    -0.27
    æIJĶ
    -0.27
    atitude
    -0.26
    ully
    -0.25
    onders
    -0.25
    è¢Ĥ
    -0.25
    åħħ满
    -0.25
    çļĦè¿ĽæŃ¥
    -0.25
    æµģæ·Į
    -0.25
    POSITIVE LOGITS
    \Page
    0.28
    thon
    0.28
    -types
    0.26
    .Types
    0.25
    rne
    0.25
     TYPES
    0.24
    /@
    0.24
     types
    0.24
     depreciation
    0.24
    	types
    0.24
    Activations Density 0.003%

    No Known Activations