© 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. 44079
    Prev
    Next
    INDEX
    Explanations

    December

    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
    çī¯
    -0.27
    ipe
    -0.27
     ÑĢай
    -0.25
    å¤ı天
    -0.25
     replacement
    -0.24
    rado
    -0.24
    нал
    -0.24
     controller
    -0.24
    主导
    -0.24
    hetto
    -0.23
    POSITIVE LOGITS
    em
    0.32
    emet
    0.30
    ema
    0.29
    娥
    0.29
    emes
    0.29
    ems
    0.28
    emble
    0.28
    emiah
    0.27
    dda
    0.26
    eme
    0.25
    Activations Density 0.020%

    No Known Activations