© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60701
    Prev
    Next
    INDEX
    Explanations

    leave followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ï¸ı
    -0.11
    ยà¸Ńม
    -0.10
    ness
    -0.10
    thon
    -0.10
    iliar
    -0.10
    обоÑĢ
    -0.09
    ivet
    -0.09
    人å±ħ
    -0.09
    rex
    -0.09
    aneously
    -0.09
    POSITIVE LOGITS
    ance
    0.11
    overs
    0.11
    äºĨä¸Ģ
    0.11
    -standing
    0.11
    yards
    0.09
    èĢĻ
    0.09
    over
    0.09
    ough
    0.09
    gun
    0.08
    uper
    0.08
    Activations Density 0.021%

    No Known Activations