© 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. 2646
    Prev
    Next
    INDEX
    Explanations

    home series, swept, three games, binary options

    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
    åĩ¿
    -0.09
    éĤ£ç§į
    -0.08
    scheme
    -0.08
    纽
    -0.08
    æľīå¤ļä¹Ī
    -0.08
    obra
    -0.08
    æ¯ı个人
    -0.08
    åįĩ
    -0.08
    è¯İ
    -0.08
    è¿ĻæĿ¡
    -0.08
    POSITIVE LOGITS
    æĪijçĽ¸ä¿¡
    0.09
    è±Ĩ
    0.09
    巴士
    0.09
    çĽĹ
    0.08
    åĥŃ
    0.08
    esk
    0.08
    èĪ¶
    0.08
    forme
    0.08
    建设çĶ¨åľ°
    0.08
    èĩŃ
    0.08
    Activations Density 0.012%

    No Known Activations