© 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. 14-TRANSCODER-HP
    7. 39543
    Prev
    Next
    INDEX
    Explanations

    somehow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    nage
    -0.31
    触
    -0.27
    æĸ¹éĿ¢
    -0.26
     influences
    -0.25
    ces
    -0.25
    æĹħ
    -0.25
    ä¸įå½ĵ
    -0.25
    zap
    -0.25
    logue
    -0.24
     factors
    -0.24
    POSITIVE LOGITS
    æįĤ
    0.26
    æĬ¢
    0.25
     qty
    0.25
    inis
    0.25
    engu
    0.25
    åŁŁåIJį
    0.25
    entlich
    0.24
    indi
    0.24
     semantics
    0.24
    Substring
    0.24
    Activations Density 1.662%

    No Known Activations