© 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. 2605
    Prev
    Next
    INDEX
    Explanations

    provides something useful

    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
    ä¸įä½Ĩ
    -0.13
    ä¸įä»ħè¦ģ
    -0.13
    ä¸įä»ħ
    -0.12
    ä¸įåĥħ
    -0.11
    ä¸įä»ħèĥ½
    -0.11
     zwar
    -0.10
    è´¨éĩıåĴĮ
    -0.10
    ä¸įä»ħåı¯ä»¥
    -0.10
    æĹ¢
    -0.09
    åİį
    -0.09
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.10
    åĺ´è§Ĵ
    0.10
    ä¸įèĩ³äºİ
    0.09
    积累
    0.09
    éĺ²çĽĹ
    0.09
    æĽ´å®¹æĺĵ
    0.08
    便äºİ
    0.08
    æĶ¶èĹı
    0.08
     brag
    0.08
    æĶ¶åħ¥
    0.08
    Activations Density 0.186%

    No Known Activations