© 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. 60812
    Prev
    Next
    INDEX
    Explanations

    fisherman and fish

    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
    ont
    -0.10
    èį»
    -0.10
    resh
    -0.10
    quat
    -0.09
    ä¸ĭçļĦ
    -0.09
    ëijĺ
    -0.09
    éĿĴæĺ¥
    -0.09
    íŀĪ
    -0.09
    çŃļ
    -0.09
    ìĤ¬íķŃ
    -0.09
    POSITIVE LOGITS
    erman
    0.17
    ermen
    0.14
    ery
    0.12
    pond
    0.10
    mong
    0.10
    ðŁIJŁ
    0.10
    åĦ¿
    0.10
    iness
    0.10
    ÑĮÑı
    0.09
    pile
    0.09
    Activations Density 0.021%

    No Known Activations