© 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. 40792
    Prev
    Next
    INDEX
    Explanations

    D/d

    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
    èĮŃ
    -0.25
     Rear
    -0.24
     shape
    -0.24
     skl
    -0.24
    æ¡Į
    -0.23
    èĥ¯
    -0.23
    à¸ģระ
    -0.23
     Acrobat
    -0.23
    为æѤ
    -0.23
    _SAMPL
    -0.23
    POSITIVE LOGITS
    ising
    0.28
    ARING
    0.27
    utto
    0.27
    éĻĨ
    0.27
    aring
    0.25
     Ryder
    0.25
    大æĪ·
    0.24
    ared
    0.24
    çļĦä¸Ģ个
    0.24
    å¹ķåIJİ
    0.23
    Activations Density 26.757%

    No Known Activations