© 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. 8525
    Prev
    Next
    INDEX
    Explanations

    one thing is done

    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
    御
    -0.10
    æŃĩ
    -0.10
    èĻĶ
    -0.10
    å¢ĥå¤ĸ
    -0.09
    çĽijäºĭä¼ļ
    -0.09
    æ»ĵ
    -0.09
    è§īæĤŁ
    -0.08
    èĥ¥
    -0.08
    å±Ī
    -0.08
    é¹ŀ
    -0.08
    POSITIVE LOGITS
    ously
    0.09
    é«ĺæ½®
    0.09
    æİĮæı¡
    0.09
    åij½
    0.09
    âĨĹ
    0.08
    arest
    0.08
    essor
    0.08
    äºĭ
    0.08
    omatic
    0.08
    IDL
    0.08
    Activations Density 0.009%

    No Known Activations