© 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. 4294
    Prev
    Next
    INDEX
    Explanations

    cqlengine

    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
    æħķ
    -0.11
    æļĤ
    -0.10
    缸è§ģ
    -0.09
    æīĢèĥ½
    -0.09
    å°ıåŃIJ
    -0.09
    è¿Ļ家ä¼Ļ
    -0.09
     Gos
    -0.09
    cie
    -0.09
    æİ¥åľ°æ°Ķ
    -0.09
    èĪ±
    -0.09
    POSITIVE LOGITS
    çĮ´
    0.09
    éĺ´å½±
    0.09
    åħ·ä½ĵæĥħåĨµ
    0.09
    west
    0.08
    äºĭæĥħ
    0.08
    æµĶ
    0.08
    åĪ·åį¡
    0.08
    ç¼Ŀ
    0.08
    èµĽåIJİ
    0.08
    rive
    0.08
    Activations Density 0.073%

    No Known Activations