© 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. 40395
    Prev
    Next
    INDEX
    Explanations

    system and systems

    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
     dozen
    -0.11
    zilla
    -0.10
    éĺĹ
    -0.10
    åĪ¶åº¦æĶ¹éĿ©
    -0.10
    asso
    -0.09
    å»ĵ
    -0.09
    æŶèĬĤ
    -0.09
    urs
    -0.09
    åĮ»ç§ij大åѦ
    -0.09
    计è¾ĥ
    -0.08
    POSITIVE LOGITS
    atics
    0.18
    atic
    0.16
    atis
    0.14
    -wide
    0.13
    ATIC
    0.12
    atically
    0.12
    ALLY
    0.12
    tle
    0.12
    ically
    0.12
    wide
    0.12
    Activations Density 0.135%

    No Known Activations