© 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. 51064
    Prev
    Next
    INDEX
    Explanations

    disposable things

    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
    è¢į
    -0.09
    ustr
    -0.09
    лав
    -0.09
    è¡·
    -0.09
    -eyed
    -0.09
    VID
    -0.09
    åŀ
    -0.09
    ìŀ¥ìĿĦ
    -0.08
    åĩºåĵģ
    -0.08
    /or
    -0.08
    POSITIVE LOGITS
    ABLE
    0.09
    å¾Ĺèµ·
    0.09
    å¾Ĺå¾Ī
    0.09
    主ä¹ī
    0.09
    alte
    0.09
     sacr
    0.09
    ç¡ķ
    0.09
    ä½ĨæĪij们
    0.09
    æ®Ĩ
    0.09
    åIJįè¯į
    0.08
    Activations Density 0.010%

    No Known Activations