© 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. 27-TRANSCODER-HP
    7. 9879
    Prev
    Next
    INDEX
    Explanations

    food recipes

    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
    Negative Logits
    agues
    -0.31
    unar
    -0.28
    parator
    -0.27
     wanting
    -0.27
    OLDER
    -0.26
    ä¾µçķ¥
    -0.25
    (bin
    -0.25
    ضØŃ
    -0.25
     agency
    -0.25
    åħ¨æĹ¥
    -0.24
    POSITIVE LOGITS
    _),
    0.28
    é²µ
    0.26
    æį¢
    0.26
    èĵĿ天
    0.25
    寻
    0.25
    occus
    0.25
    ptive
    0.25
    Stamp
    0.24
    edly
    0.24
    sembler
    0.24
    Activations Density 0.009%

    No Known Activations