© 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. 2908
    Prev
    Next
    INDEX
    Explanations

    small things and improvements

    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
    ä»ħä»ħ
    -0.10
     Eag
    -0.10
    è¶Ł
    -0.09
    æ´ij
    -0.09
    éŀŃ
    -0.09
    DisplayStyle
    -0.09
    (ed
    -0.08
     ÐŀÑĩ
    -0.08
    çī¹æ®ĬæĥħåĨµ
    -0.08
    èĤ¥
    -0.08
    POSITIVE LOGITS
    ä¸ĢçĤ¹
    0.11
    å°ıäºĭ
    0.10
    ç»ĨèĬĤ
    0.10
     details
    0.10
    çIJIJ
    0.09
    eyer
    0.09
    ä¸Ģé»ŀ
    0.09
    èĽĽ
    0.09
    åĴĸ
    0.09
    æģĻ
    0.09
    Activations Density 0.190%

    No Known Activations