© 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. 59453
    Prev
    Next
    INDEX
    Explanations

    entitled to or eligible for

    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
    污æŁĵ
    -0.09
    pb
    -0.08
    ettes
    -0.08
    ãģ½
    -0.08
    bei
    -0.08
    à´Ł
    -0.08
    æĺ¯éĿŀ
    -0.08
    ãģĸ
    -0.08
    nic
    -0.08
    HEN
    -0.07
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩ
    0.10
    zza
    0.10
     паÑĢа
    0.10
    ities
    0.09
    ä¿¡èµĸ
    0.09
    uba
    0.09
    å²Ľä¸Ĭ
    0.09
    주ìĿĺ
    0.09
    _MORE
    0.09
    SHARE
    0.09
    Activations Density 0.007%

    No Known Activations