© 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. 24241
    Prev
    Next
    INDEX
    Explanations

    issued guidance on

    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
    oston
    -0.08
     Abrams
    -0.08
    æµĨ
    -0.08
    affle
    -0.08
    æĶ¾å¤§
    -0.08
    é¦Ļæ°´
    -0.08
    باط
    -0.08
    zek
    -0.08
    大å±Ģ
    -0.08
    ifiable
    -0.07
    POSITIVE LOGITS
    åı¸
    0.10
    ÑĤе
    0.10
    пиÑģание
    0.09
     ade
    0.09
    _PRI
    0.09
    flash
    0.09
     Flash
    0.08
    FLASH
    0.08
    èݼ
    0.08
     pretend
    0.08
    Activations Density 0.014%

    No Known Activations