© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9945
    Prev
    Next
    INDEX
    Explanations

    customers and clients

    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
    鬣
    -0.09
    éĻIJ度
    -0.09
    ä¼ļå±ķ
    -0.09
     CFL
    -0.09
    ivot
    -0.08
    å±ĤéĿ¢
    -0.08
    对æĸ¹
    -0.08
    å¼Ĺ
    -0.08
    hawk
    -0.08
    æŁĵ
    -0.08
    POSITIVE LOGITS
    å·²æľī
    0.11
    éģį
    0.10
    çļĦä¸ĢéĿ¢
    0.10
    屡
    0.10
    éģįå¸ĥ
    0.09
    å°±æĺ¯åĽłä¸º
    0.09
    ä¸Ģèĩ´å¥½è¯Ħ
    0.09
    æĹłæķ°
    0.09
    æµ·åĨħå¤ĸ
    0.09
     reason
    0.09
    Activations Density 0.077%

    No Known Activations