© 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. 30469
    Prev
    Next
    INDEX
    Explanations

    generation of

    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
    oen
    -0.09
    éĵ
    -0.09
    ç¬ı
    -0.09
    oad
    -0.09
    landers
    -0.09
    ä¸ĢçĤ¹åĦ¿
    -0.09
    oc
    -0.08
    ç¾İ人
    -0.08
    éĤĪ
    -0.08
    ä¸Ģç§Ĵ
    -0.08
    POSITIVE LOGITS
    ä¸Ģ大æī¹
    0.14
    è¿Ļæī¹
    0.12
    ä¸Ģæī¹
    0.11
    大æī¹
    0.11
    é«ĺç´łè´¨
    0.10
     полно
    0.10
    äºĨä¸Ģæī¹
    0.10
    äº¤æĽ¿
    0.10
    æĸ°ä¸Ģ代
    0.09
    æºIJæºIJä¸įæĸŃ
    0.09
    Activations Density 0.055%

    No Known Activations