© 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. 60589
    Prev
    Next
    INDEX
    Explanations

    ft

    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
    ç´§åĩij
    -0.09
    aler
    -0.09
     dần
    -0.08
    éĩįä¸Ń
    -0.08
    ese
    -0.08
    çī¹éķ¿
    -0.08
    忽
    -0.08
    å½ĵåľ°çļĦ
    -0.08
    ç»Ħç»ĩå®ŀæĸ½
    -0.08
    Sem
    -0.08
    POSITIVE LOGITS
    agos
    0.09
    CRY
    0.09
    ORAGE
    0.09
    è¿ĺä¸įæĺ¯
    0.09
    对äºİæĪij们
    0.09
    ÐIJÐĿ
    0.09
    agate
    0.09
    kok
    0.08
    boss
    0.08
    antz
    0.08
    Activations Density 0.286%

    No Known Activations