© 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. 47721
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and algebra

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æŀŃ
    -0.10
    ä¸ľæµ·
    -0.10
    terra
    -0.09
    éĩijå±±
    -0.09
    åij¼
    -0.09
     pneum
    -0.09
    èijĨ
    -0.08
    é¹ĺ
    -0.08
    rome
    -0.08
     Metropolitan
    -0.08
    POSITIVE LOGITS
    CLA
    0.09
    æĴ¸
    0.09
    åıĹä¼Ĺ
    0.09
    ally
    0.08
    utow
    0.08
     Ranch
    0.08
    ecret
    0.08
    å®Ī
    0.08
    ç§ĺå¯Ĩ
    0.08
    å¿ĥæĦ¿
    0.08
    Activations Density 0.009%

    No Known Activations