© 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. 19402
    Prev
    Next
    INDEX
    Explanations

    evidence that

    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
    _GF
    -0.08
     поб
    -0.08
     Protected
    -0.08
    åŀ¦
    -0.08
    .setter
    -0.08
    rale
    -0.08
    çī§
    -0.08
    ·æĸ°
    -0.08
    ä¸ªå·¥ä½ľ
    -0.08
    æĬĬæīĭ
    -0.08
    POSITIVE LOGITS
    æĶ¯æĮģåĬĽåº¦
    0.11
    åıį驳
    0.10
    æĶ¯æĮģ
    0.10
     Dep
    0.10
    说æľį
    0.10
    Dep
    0.09
    åĬ¨æijĩ
    0.09
    æ²¹èĦĤ
    0.09
    çļĦæĶ¯æĮģ
    0.09
    åĢ¾åIJijäºİ
    0.09
    Activations Density 0.104%

    No Known Activations