© 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. 23975
    Prev
    Next
    INDEX
    Explanations

    know well

    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
    Not in Any Lists

    No Comments

    Negative Logits
    anko
    -0.10
    ç¾İ
    -0.09
    æłĵ
    -0.09
    assen
    -0.08
    anka
    -0.08
    0
    -0.08
    esus
    -0.08
    eds
    -0.08
    bek
    -0.08
    elda
    -0.08
    POSITIVE LOGITS
    éĢı
    0.15
    çŁ¥å·±
    0.12
    çĨŁæĤī
    0.11
    çĨŁ
    0.11
    ç¨ĭ度
    0.11
    çļĦç¨ĭ度
    0.11
    æĬĬæı¡
    0.11
     влад
    0.10
    è°Ļ
    0.10
    쯤
    0.10
    Activations Density 0.073%

    No Known Activations