© 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. 56990
    Prev
    Next
    INDEX
    Explanations

    received a notice/call/email

    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
    è½»æĺĵ
    -0.09
     легко
    -0.09
    bol
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
    èĩªçIJĨ
    -0.09
    æľĢ容æĺĵ
    -0.09
    å¦Ħ
    -0.09
    _userdata
    -0.08
    ä¿Ŀå®Ī
    -0.08
    æĶ¶åıĸ
    -0.08
    POSITIVE LOGITS
    åĪ®
    0.10
    éĢ®
    0.10
    æĢ¥éľĢ
    0.09
    ç´§æĢ¥
    0.09
    /request
    0.09
    èĢĹ
    0.09
    éĻĮçĶŁ
    0.08
    æĸ°çļĦ
    0.08
    åĽ¢
    0.08
    GES
    0.08
    Activations Density 0.101%

    No Known Activations