© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31142
    Prev
    Next
    INDEX
    Explanations

    parade

    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
    Not in Any Lists

    No Comments

    Negative Logits
    lessly
    -0.11
    eric
    -0.09
    çĿĽ
    -0.09
    eness
    -0.08
    ê¹IJ
    -0.08
    ness
    -0.08
    åĪ°æľĢåIJİ
    -0.08
    楮
    -0.08
    å½¼
    -0.08
    ×ķף
    -0.08
    POSITIVE LOGITS
    ë¡Ń
    0.11
    stration
    0.10
    loff
    0.10
     ва
    0.09
    osas
    0.09
    icular
    0.09
    jectives
    0.09
    zik
    0.09
    anus
    0.09
    -minded
    0.09
    Activations Density 0.008%

    No Known Activations