© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29239
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     scene
    -0.29
     gross
    -0.28
    -cn
    -0.28
    filer
    -0.27
     terme
    -0.26
    赤
    -0.26
    篦
    -0.26
    ä¸į妨
    -0.26
    主页
    -0.25
    æ±Łèĭı
    -0.25
    POSITIVE LOGITS
    otherwise
    0.25
    аÑĢам
    0.25
     (!_
    0.25
    Infrastructure
    0.25
    åİ»æī¾
    0.24
     tuyến
    0.24
    ç°§
    0.24
    avo
    0.24
     Otherwise
    0.24
    åIJ¦åĪĻ
    0.23
    Activations Density 0.464%

    No Known Activations