© 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. 54149
    Prev
    Next
    INDEX
    Explanations

    your or my personal information

    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
    nds
    -0.09
    æīĥ
    -0.09
    å¸®ä½ł
    -0.09
    å±ĢéĿ¢
    -0.09
    aal
    -0.09
    è¶Ĭåıij
    -0.08
    æ¢Ń
    -0.08
    æľī人说
    -0.08
    ossa
    -0.08
    à¹ģà¸Ł
    -0.08
    POSITIVE LOGITS
    å§ĵåIJį
    0.10
    æĶ¾åģĩ
    0.09
     name
    0.09
    å¹´é¾Ħ
    0.09
    æīĢåľ¨åľ°
    0.09
    ä»İä¸ļ
    0.09
    æīĭæľºåı·
    0.09
    éºĩ
    0.09
    åıįæĺł
    0.08
    èĤ¤èī²
    0.08
    Activations Density 0.042%

    No Known Activations