© 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. 22124
    Prev
    Next
    INDEX
    Explanations

    parentheses or list 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
    çĤī
    -0.09
    Verb
    -0.08
    ÑıÑħ
    -0.08
    å¾Ĵ
    -0.08
    loy
    -0.08
    çĪIJ
    -0.08
    åĴ«
    -0.08
     eens
    -0.08
    æŃ¥
    -0.08
    误ä¼ļ
    -0.08
    POSITIVE LOGITS
    ç¥Ģ
    0.10
    è¢Ĥ
    0.09
    礼æĭľ
    0.09
    çķĽ
    0.08
    èĤĦ
    0.08
    çĽ¸å¯¹è¾ĥ
    0.08
    éī
    0.08
    äºĨåIJĹ
    0.08
    æľīæīĢ帮åĬ©
    0.08
    åī¯
    0.08
    Activations Density 0.162%

    No Known Activations