© 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. 30941
    Prev
    Next
    INDEX
    Explanations

    number of items

    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
    水管
    -0.10
    æ¯ĶåĪ©
    -0.09
     Schultz
    -0.09
    å°ıåŃIJ
    -0.09
     plurality
    -0.09
    è¡Ĺä¸Ĭ
    -0.09
    æľīåĩłä¸ª
    -0.09
    ä¹ĭåŁİ
    -0.09
    ÑıÑĤ
    -0.08
    거리
    -0.08
    POSITIVE LOGITS
    è±ģ
    0.10
    ä¸İæѤ
    0.09
    æµ·åĨħå¤ĸ
    0.08
    ÒĻ
    0.08
    大大å°ıå°ı
    0.08
    æľīæľŁ
    0.08
    å¯Įæľī
    0.08
    æĢ«
    0.08
    Ops
    0.08
    ish
    0.08
    Activations Density 0.172%

    No Known Activations