© 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. 9760
    Prev
    Next
    INDEX
    Explanations

    file names and code

    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
    otropic
    -0.29
    _AST
    -0.25
    äºĭä¸ļåıijå±ķ
    -0.24
    ä¸Ģ头
    -0.23
    ussion
    -0.23
    çŁ³
    -0.23
    容纳
    -0.23
    ä¸ĸä¸Ĭ
    -0.23
    ast
    -0.23
    ä»Ļ
    -0.23
    POSITIVE LOGITS
    aison
    0.27
    çĶ¨éĢĶ
    0.26
    ãĥijãĤ¿
    0.25
    æݨèĸ¦
    0.25
    æݨèįIJ
    0.25
    rade
    0.24
    ucid
    0.24
    EEP
    0.24
    andel
    0.24
    Recommend
    0.24
    Activations Density 0.000%

    No Known Activations