© 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. 9912
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    带头
    -0.32
    驼
    -0.29
    没æľī人
    -0.28
    scores
    -0.28
    score
    -0.26
    没æľīä»Ģä¹Ī
    -0.25
     scores
    -0.25
     flakes
    -0.25
    crypt
    -0.24
    èµĦæºIJä¼ĺåĬ¿
    -0.24
    POSITIVE LOGITS
    ล
    0.26
    (/^
    0.26
     Ell
    0.26
    ä¸Ģèµ·
    0.25
     Nets
    0.25
    åīįæīĢ
    0.24
    åĵªè£¡
    0.24
    ento
    0.24
    (New
    0.23
     lid
    0.23
    Activations Density 0.006%

    No Known Activations