© 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. 4189
    Prev
    Next
    INDEX
    Explanations

    email from. name is. address is

    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
    isman
    -0.11
    æłĵ
    -0.10
    omy
    -0.09
    æĭ´
    -0.09
    æľī幸
    -0.09
    kö
    -0.09
    é«ĺåİŁ
    -0.09
    åłĻ
    -0.08
    dess
    -0.08
    GLOSS
    -0.08
    POSITIVE LOGITS
    æŃ£è§Ħ
    0.11
    èĩªç§°
    0.11
    æĿ¥åİĨ
    0.09
    èģ·
    0.09
    èľĢ
    0.09
    æŁIJæŁIJ
    0.09
    çļĦ身份
    0.09
    à¸ģระà¸Ĺ
    0.09
    è¿ĩæĿ¥
    0.09
    身份
    0.09
    Activations Density 0.041%

    No Known Activations