© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9831
    Prev
    Next
    INDEX
    Explanations

    how it explains something

    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
    åĵ¨
    -0.12
    汩
    -0.12
    éĤ£ç§į
    -0.09
    åİĿ
    -0.09
    é£ŀç¿Ķ
    -0.08
    çĶľç¾İ
    -0.08
    åĬ±å¿Ĺ
    -0.08
     اÙĦجارÙĬ
    -0.08
    çľĭçĤ¹
    -0.08
    èIJ¥åķĨ
    -0.08
    POSITIVE LOGITS
    éĩįè§Ĩ
    0.10
    åıªæľī
    0.09
    éĨ
    0.09
    å·®çĤ¹
    0.08
    åı¯è§ģ
    0.08
    è§īå¾Ĺå¾Ī
    0.08
    ORAGE
    0.08
    ROP
    0.08
    æĪijä¸įæĺ¯
    0.08
    è¿Ļæĺ¯æĪij
    0.08
    Activations Density 0.034%

    No Known Activations