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. 27-TRANSCODER-HP
    4. 857
    Prev
    Next
    INDEX
    Explanations

    Code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¾ŀ
    -0.95
     embarrassment
    -0.88
     shame
    -0.86
     embarrassed
    -0.82
    èĢ»
    -0.80
     ashamed
    -0.80
     embarrassing
    -0.78
    ä¸į好æĦıæĢĿ
    -0.77
    害ç¾ŀ
    -0.71
     shameful
    -0.69
    POSITIVE LOGITS
    ucid
    0.30
     przec
    0.26
    oux
    0.26
     pos
    0.25
    iku
    0.24
    max
    0.23
    -density
    0.23
    ÙģØ§Øª
    0.23
    ?=.*
    0.23
    EFF
    0.23
    Activations Density 0.007%

    No Known Activations