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. 92803
    Prev
    Next
    INDEX
    Explanations

    most/best

    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
    agus
    -0.26
    ä¸İæĹ¶
    -0.26
     endforeach
    -0.26
    -basket
    -0.24
     hakk
    -0.24
    deaux
    -0.24
    å¤©åľ°
    -0.23
    æĭ¯
    -0.23
    uden
    -0.23
    è´Ł
    -0.23
    POSITIVE LOGITS
    otel
    0.33
     Shirley
    0.28
    rolley
    0.27
    å¾µ
    0.26
     Herman
    0.25
    æĿ¥è¢Ń
    0.24
    çĸ¾
    0.24
    .commit
    0.23
    orio
    0.23
    çħ®
    0.23
    Activations Density 0.004%

    No Known Activations