© 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. 6227
    Prev
    Next
    INDEX
    Explanations

    Source Code Form is subject

    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
    ÑģпоÑģоб
    -0.10
    ALA
    -0.09
    INDOW
    -0.09
    sgi
    -0.08
    tas
    -0.08
    reeze
    -0.08
    AVE
    -0.08
    éĿŀ常好
    -0.08
    oved
    -0.08
    åIJ»
    -0.08
    POSITIVE LOGITS
     opaque
    0.09
    ç®Ģ称
    0.09
     Tmin
    0.08
     Willis
    0.08
    ä½ķåĨµ
    0.08
     Jian
    0.07
    éĿĴå¹´
    0.07
    ç«ĭå¿Ĺ
    0.07
     spr
    0.07
    ver
    0.07
    Activations Density 1.390%

    No Known Activations