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. 24600
    Prev
    Next
    INDEX
    Explanations

    code and internet

    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
    áŀĽ
    -0.25
    åľ¨åĮĹ京
    -0.25
    DR
    -0.25
     tá»ij
    -0.25
    ä½Ĩä¸įéĻIJäºİ
    -0.25
    Tests
    -0.24
    èħ¿
    -0.24
    æĸĭ
    -0.24
    µ
    -0.24
    ç»´æĬ¤
    -0.24
    POSITIVE LOGITS
    æĮĩå¼ķ
    0.30
     advis
    0.28
    adamente
    0.28
    arning
    0.25
    aan
    0.24
    AAD
    0.24
    EObject
    0.24
    OLER
    0.24
     Spart
    0.24
    orge
    0.24
    Activations Density 0.001%

    No Known Activations