© 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. 40410
    Prev
    Next
    INDEX
    Explanations

    street names

    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
    ä¸Ĭå®ĺ
    -0.10
    ä¸įæĢķ
    -0.09
    åĺŁ
    -0.09
    æĥij
    -0.08
    ripp
    -0.08
    骡
    -0.08
    berger
    -0.08
    åĨįåİ»
    -0.08
    èļĢ
    -0.08
    è·¯è¿ĩ
    -0.08
    POSITIVE LOGITS
    è¤IJ
    0.09
    æĻ®
    0.08
    éĹ»
    0.08
    驹
    0.08
    éĹ´æİ¥
    0.08
    enk
    0.08
    oub
    0.08
    ç§ģèĩª
    0.08
    åĪĽæĬķ
    0.08
    iale
    0.08
    Activations Density 0.034%

    No Known Activations