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. 10431
    Prev
    Next
    INDEX
    Explanations

    'll

    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
    æĬł
    -0.29
    [*
    -0.27
    åīĭ
    -0.26
    morph
    -0.24
    ä»ĸ们ä¼ļ
    -0.24
    —they
    -0.24
     conceive
    -0.23
     resides
    -0.23
     NOR
    -0.23
    inalg
    -0.23
    POSITIVE LOGITS
    -actions
    0.29
    rocessing
    0.27
    odia
    0.26
    _instructions
    0.25
    -backend
    0.24
    IEL
    0.24
     Permissions
    0.24
    许
    0.24
     %"
    0.24
    actions
    0.23
    Activations Density 0.004%

    No Known Activations