© 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. 1331
    Prev
    Next
    INDEX
    Explanations

    finding tips and options

    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
    å¿Ŀ
    -0.09
    ä¸įåħģ许
    -0.09
    èµłéĢģ
    -0.08
    饯
    -0.08
    è¿ĵ
    -0.08
    æ´Ĺæīĭ
    -0.08
    èijŃ
    -0.08
    æĤĮ
    -0.08
    第ä¸ī代
    -0.08
    åħģ许
    -0.08
    POSITIVE LOGITS
    æIJľç´¢
    0.14
    æĮijéĢī
    0.13
    æī¾åĪ°
    0.13
    寻æī¾
    0.12
    æī¾åĪ°äºĨ
    0.12
    éĢīåĩº
    0.12
    ä¹°åĪ°
    0.11
     поиÑģк
    0.11
    çļĦéĢīæĭ©
    0.11
    åľ¨ç½ijä¸Ĭ
    0.11
    Activations Density 0.170%

    No Known Activations