© 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. 40375
    Prev
    Next
    INDEX
    Explanations

    need / needed states or requirements

    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
    éģIJ
    -0.10
    èĬĴ
    -0.09
    SHIFT
    -0.09
    巴士
    -0.09
    åĮ£
    -0.09
    çĥĻ
    -0.09
     söz
    -0.08
    Ñħи
    -0.08
    -spin
    -0.08
    changer
    -0.08
    POSITIVE LOGITS
    æĢ¥éľĢ
    0.14
     desperately
    0.12
    缺å°ij
    0.12
    äºŁ
    0.11
     desperate
    0.11
    è¿«åĪĩ
    0.10
     badly
    0.10
    çĸıéĢļ
    0.10
    çļĦçģµéŃĤ
    0.09
    紧缺
    0.09
    Activations Density 0.047%

    No Known Activations