© 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. 44252
    Prev
    Next
    INDEX
    Explanations

    white

    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
    å®ŀåľ¨
    -0.27
    иÑĩно
    -0.26
    æĮĩæĮ¥
    -0.26
     MLM
    -0.24
    AMY
    -0.24
    Abr
    -0.24
    å¥Ħ
    -0.23
    ä¸ļ
    -0.23
    azy
    -0.23
    opoulos
    -0.23
    POSITIVE LOGITS
     Plates
    0.28
    pres
    0.28
    plate
    0.27
    Plate
    0.27
     plates
    0.27
    ÑħоÑĤ
    0.26
    pine
    0.26
    Cargo
    0.26
     Gast
    0.26
    åĨĴçĿĢ
    0.26
    Activations Density 0.002%

    No Known Activations