© 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. 49329
    Prev
    Next
    INDEX
    Explanations

    usually, typically, generally

    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
    çĭIJ
    -0.11
    ç´¯äºĨ
    -0.11
    é¹Ĺ
    -0.10
    å¼Ģçİ©ç¬ij
    -0.10
    èĸ®
    -0.09
    è¡ħ
    -0.09
     бÑĥд
    -0.09
    èļ¤
    -0.09
    è°Ķ
    -0.09
    ä¹ĭåŁİ
    -0.09
    POSITIVE LOGITS
    æĮĤåı·
    0.09
    é»ĺé»ĺ
    0.09
    æī®æ¼Ķ
    0.09
    ä¸įèĤ¯
    0.08
    å½Ĵ
    0.08
    éļ¶å±ŀäºİ
    0.08
    ottom
    0.08
    æĪij没
    0.08
    ilies
    0.08
    (Boolean
    0.08
    Activations Density 0.122%

    No Known Activations