© 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. 31-TRANSCODER-HP
    7. 17963
    Prev
    Next
    INDEX
    Explanations

    article

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     suddenly
    -0.29
    çªģçĦ¶
    -0.27
    ely
    -0.27
     unexpectedly
    -0.26
    ori
    -0.25
    weis
    -0.25
    apiro
    -0.25
    ÑĨиалÑĮно
    -0.25
     visually
    -0.25
     Rai
    -0.25
    POSITIVE LOGITS
     practice
    0.35
     practise
    0.33
    åĪĨãģij
    0.33
    æĪĺçķ¥æĢ§
    0.31
     strategic
    0.30
    -manager
    0.29
    ä¸īåĪĨ
    0.29
    practice
    0.29
    strategy
    0.29
    æ¸ij
    0.28
    Activations Density 1.113%

    No Known Activations