© 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. 4312
    Prev
    Next
    INDEX
    Explanations

    in followed by location or context

    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
    ivr
    -0.10
    èµŀèµı
    -0.10
    èĪŀåı°
    -0.09
    Į¨
    -0.09
    ihu
    -0.09
    Bes
    -0.09
     Dank
    -0.08
    èı¯
    -0.08
     Bes
    -0.08
     поÑĢ
    -0.08
    POSITIVE LOGITS
    æĹłæīĢ
    0.10
    é¦Ĩ
    0.09
    äºĨä¸Ģ份
    0.09
    ç»
    0.09
    å®ĺ宣
    0.09
    è§īå¾Ĺå¾Ī
    0.08
    éĻ¢éĻ¢éķ¿
    0.08
    çļĦåIJĦ项
    0.08
    ä½ļ
    0.08
    rena
    0.08
    Activations Density 0.171%

    No Known Activations