© 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. 56676
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    å§Ķä¼ļ
    -0.26
     slump
    -0.24
    æľ¬æĬ¥è®¯
    -0.23
    Ķ
    -0.23
     syll
    -0.23
     báºŃc
    -0.23
    ÇIJ
    -0.23
    raries
    -0.23
    bak
    -0.22
    é«ĺä»·
    -0.22
    POSITIVE LOGITS
    0.47
     thirty
    0.44
     sixty
    0.42
     fifteen
    0.40
     forty
    0.40
     twelve
    0.39
     approximately
    0.38
     fifty
    0.38
    ä¸īåįģ
    0.36
     twenty
    0.36
    Activations Density 0.001%

    No Known Activations