© 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. 56675
    Prev
    Next
    INDEX
    Explanations

    Work performance

    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
    Not in Any Lists

    No Comments

    Negative Logits
     aup
    -0.30
    æıIJé«ĺ
    -0.28
    empor
    -0.27
     Improve
    -0.27
    eec
    -0.26
    upo
    -0.26
    ein
    -0.24
    æ¥ł
    -0.24
    æĹ¶ä»£çļĦ
    -0.24
    å¾Ī好çļĦ
    -0.24
    POSITIVE LOGITS
     performance
    0.69
    æĢ§èĥ½
    0.66
     efficiency
    0.65
     accuracy
    0.60
    æķĪçİĩ
    0.59
     quality
    0.58
     morale
    0.58
    performance
    0.57
     productivity
    0.57
     usability
    0.55
    Activations Density 0.005%

    No Known Activations