© 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. 55885
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    æĿµ
    -0.11
    è°Ł
    -0.11
    æĽ´å¤ļä¿¡æģ¯
    -0.10
    åı¦ä¸Ģç§į
    -0.10
    ä½ľåĩºäºĨ
    -0.10
    ä¹ŁæĪIJ为
    -0.10
    çݰ代çī©æµģ
    -0.10
    ä¸ĸçķĮåIJĦåľ°
    -0.10
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.10
    è°Ĺ
    -0.10
    POSITIVE LOGITS
    ä¸ĢéĿ¢
    0.09
    夹
    0.08
    æŁIJ
    0.08
    å¤ļä¹Ī
    0.08
    ä¸Ģè¾¹
    0.08
    fol
    0.08
    å°±æľī
    0.07
     might
    0.07
     fol
    0.07
    LTE
    0.07
    Activations Density 0.267%

    No Known Activations