© 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. 33-TRANSCODER-HP
    7. 52794
    Prev
    Next
    INDEX
    Explanations

    say number 2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ".↵
    -0.28
    ä¸Ģ举
    -0.26
     sophistic
    -0.26
    æľªæĪIJ
    -0.26
     ..."↵
    -0.25
    æ¦ľ
    -0.25
    ariat
    -0.24
     fatally
    -0.24
     ^.
    -0.24
    å¿«æĬ¥
    -0.23
    POSITIVE LOGITS
     par
    0.27
     Dickinson
    0.24
     story
    0.24
    èĹľ
    0.24
    ’il
    0.23
    ÑĭÑĤа
    0.23
     novel
    0.23
     company
    0.22
     ÑĢаÑģÑģ
    0.22
     regional
    0.22
    Activations Density 0.277%

    No Known Activations