© 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. 626
    Prev
    Next
    INDEX
    Explanations

    reasons to

    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
    oug
    -0.09
    æĢ»ç®Ĺ
    -0.09
    tes
    -0.09
    ords
    -0.09
    åĽŀåIJĪ
    -0.09
    RESS
    -0.08
     Schwe
    -0.08
    ħ§
    -0.08
    ãģłãģ£ãģ¦
    -0.08
    pe
    -0.08
    POSITIVE LOGITS
    ä¸įå¿ĺ
    0.11
    åģľçķĻåľ¨
    0.11
    æĦŁåĪ°
    0.10
    æĭħ忧
    0.10
    æĭħå¿ĥ
    0.10
    åħ³åĪĩ
    0.10
    亲è¿ij
    0.10
    åħ³æ³¨
    0.09
    æłĿ
    0.09
    ä¾£
    0.09
    Activations Density 0.018%

    No Known Activations