© 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. 35-TRANSCODER-HP
    7. 40635
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Daily
    -0.46
     daily
    -0.46
    Daily
    -0.40
     (
    -0.38
    daily
    -0.37
    ub
    -0.36
    æ¯ıæĹ¥
    -0.35
    æ¯ı天
    -0.35
    ak
    -0.35
    aff
    -0.34
    POSITIVE LOGITS
     entirety
    0.31
    ä¸įä¹ı
    0.30
    éĿŀ常å¤ļçļĦ
    0.28
    å¾Īæ¸ħæ¥ļ
    0.28
    &w
    0.28
    å¾Īæĥ³
    0.28
     inconsistency
    0.28
    æĭ¯
    0.27
    ä¹ŁéľĢè¦ģ
    0.27
    åħħè£ķ
    0.27
    Activations Density 0.183%

    No Known Activations