© 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. 40361
    Prev
    Next
    INDEX
    Explanations

    frame rate

    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
    缤
    -0.10
     поÑģл
    -0.10
    èĢ³æľµ
    -0.09
    çªģåĩ»
    -0.09
    æľįä»İ
    -0.09
    oner
    -0.09
     Hubb
    -0.09
    íģ°
    -0.09
    çĽĺ
    -0.09
    leta
    -0.09
    POSITIVE LOGITS
    æģĴ
    0.09
    å«ī
    0.09
    顽
    0.09
    chron
    0.09
    à¹Ħหล
    0.08
    åªļ
    0.08
    åºıå¹ķ
    0.08
    Smooth
    0.08
    odyn
    0.08
    PEG
    0.08
    Activations Density 0.078%

    No Known Activations