© 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. 2392
    Prev
    Next
    INDEX
    Explanations

    moved to or into

    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
    æ·¡æ·¡
    -0.09
    éĢĭ
    -0.09
    aten
    -0.09
     вн
    -0.09
    sgiving
    -0.09
    Sport
    -0.09
    ption
    -0.09
    ergic
    -0.09
    峡
    -0.09
     Balt
    -0.08
    POSITIVE LOGITS
    åĢ¡å¯¼
    0.09
    说åĪ°
    0.09
    _into
    0.09
     into
    0.09
    æĪijçĪ±ä½ł
    0.09
    æĿ¥çļĦ
    0.09
    åIJİçļĦ
    0.09
    èĩ³æѤ
    0.09
    able
    0.08
    åħ¥ä½ı
    0.08
    Activations Density 0.039%

    No Known Activations