© 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. 2119
    Prev
    Next
    INDEX
    Explanations

    knew I

    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
    æĪijçİ°åľ¨
    -0.09
    achi
    -0.09
    _VF
    -0.08
    åŃĿ
    -0.08
    ä¸Ģ人
    -0.08
    /javascript
    -0.08
    IFS
    -0.08
    çĶ¨å¾®ä¿¡
    -0.08
    ções
    -0.08
    ]][
    -0.08
    POSITIVE LOGITS
    è¿Ļå°±æĺ¯
    0.12
    æĢİä¹ĪåĽŀäºĭ
    0.11
    ä¸įä¼ļåĨį
    0.10
    è¿Ļä¸įæĺ¯
    0.09
    åĢ¼å¾Ĺ
    0.09
    éĤ£ä¸ĢåĪ»
    0.09
    ç»Ŀ对æĺ¯
    0.09
    éĻĶ
    0.09
    è¦ģåģļ
    0.09
    ä¸ĢåĪ»
    0.09
    Activations Density 0.034%

    No Known Activations