© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33492
    Prev
    Next
    INDEX
    Explanations

    never to pick

    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
    ä¸¥æł¼çļĦ
    -0.10
    æºIJæºIJ
    -0.10
    oley
    -0.09
    æ·»
    -0.09
    resenter
    -0.09
    ä¹Łåıªæĺ¯
    -0.08
     Harden
    -0.08
    mall
    -0.08
    åIJ¹
    -0.08
     strict
    -0.08
    POSITIVE LOGITS
    åĨįä¹Łä¸į
    0.13
    åĨįä¹Ł
    0.12
    ingly
    0.11
    以å¾Į
    0.11
    åĨįä¹Łæ²¡æľī
    0.11
    ç»ĪçĶŁ
    0.10
    ä»İæѤ
    0.10
    以åIJİ
    0.10
    ä»ĬåIJİ
    0.10
     EVER
    0.09
    Activations Density 0.027%

    No Known Activations