© 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. 32-TRANSCODER-HP
    7. 44006
    Prev
    Next
    INDEX
    Explanations

    rem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĭį
    -0.35
     Dort
    -0.28
    æľºåĻ¨
    -0.28
    cam
    -0.27
     Plate
    -0.27
    cor
    -0.26
     Hardware
    -0.26
    çĽĴåŃIJ
    -0.26
    宾
    -0.26
    Memcpy
    -0.25
    POSITIVE LOGITS
    iking
    0.29
    itian
    0.28
    iber
    0.26
    LObject
    0.25
    arium
    0.25
    lick
    0.25
    icum
    0.25
    ä½ľé£İ建设
    0.25
    ätz
    0.25
    elon
    0.25
    Activations Density 0.001%

    No Known Activations