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. 11-TRANSCODER-HP
    4. 46428
    Prev
    Next
    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (!_
    -0.30
     Pron
    -0.28
    (!_
    -0.28
    缴èIJ¥
    -0.27
     !_
    -0.25
    _Link
    -0.25
    riott
    -0.25
    _air
    -0.24
     withObject
    -0.24
    éĥijå·ŀå¸Ĥ
    -0.24
    POSITIVE LOGITS
    模ç³Ĭ
    0.27
     SUMMARY
    0.27
    unnel
    0.26
    æĵ¦æĭŃ
    0.26
     fores
    0.26
    æĻ®æŁ¥
    0.26
     Economy
    0.26
     vi
    0.26
     panorama
    0.26
     Vi
    0.25
    Activations Density 0.016%

    No Known Activations