© 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. 22-TRANSCODER-HP
    7. 130943
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egot
    -0.31
    æį¢æĿ¥
    -0.25
    ä¼ģä¸ļæıIJä¾Ľ
    -0.25
     Curtain
    -0.25
    该æĿij
    -0.24
    eping
    -0.24
    mailto
    -0.24
     GIVEN
    -0.23
     BRO
    -0.23
    è¿Ļé¦ĸ
    -0.23
    POSITIVE LOGITS
    ç²¾
    0.28
    å¤ĸ
    0.27
    çĿĢ
    0.27
    继ç»Ń
    0.26
    èĢĮæĺ¯
    0.26
    .ResultSet
    0.25
    å¿«
    0.25
    ç»ĵ
    0.25
     unm
    0.25
    è¿Ľä¸ĢæŃ¥
    0.24
    Activations Density 0.010%

    No Known Activations