© 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. 61377
    Prev
    Next
    INDEX
    Explanations

    legal challenges and declarations

    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
    SSF
    -0.10
     пок
    -0.09
    SSI
    -0.09
    对æѤ
    -0.08
    paginate
    -0.08
    èŃ
    -0.08
    iddle
    -0.08
    closing
    -0.08
    æIJ¬è¿IJ
    -0.08
    елÑı
    -0.08
    POSITIVE LOGITS
    æĹłæķĪ
    0.11
    ä»»æĢ§
    0.10
    人çī©
    0.10
    æĬ¤èº«
    0.09
    تÙĩ
    0.09
    Launcher
    0.09
    dorf
    0.09
    é»ijæģ¶
    0.09
    æĮ¡
    0.09
    	eval
    0.09
    Activations Density 0.030%

    No Known Activations