© 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. 55358
    Prev
    Next
    INDEX
    Explanations

    which is/are

    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
    lix
    -0.10
     паÑĢа
    -0.10
    åĩºä¼ļ
    -0.09
    æ¸ħæ°´
    -0.09
    ç¬ijéģĵ
    -0.09
    èİ«è¿ĩäºİ
    -0.09
    åĪĻæĺ¯
    -0.09
    åı©
    -0.09
    åľ¨éĤ£éĩĮ
    -0.09
    åīĩ
    -0.08
    POSITIVE LOGITS
     fab
    0.10
    çĨŁæĤī
    0.09
    è¿Īåĩº
    0.09
    ä½ľèĢħæľ¬äºº
    0.08
    olls
    0.08
    追æ±Ĥ
    0.08
    åIJij社ä¼ļ
    0.08
    æİĮæı¡äºĨ
    0.08
    è¡·
    0.08
    oret
    0.08
    Activations Density 0.105%

    No Known Activations