© 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. 23267
    Prev
    Next
    INDEX
    Explanations

    non-english or numbers

    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
     íĺ¸
    -0.10
    Criterion
    -0.09
     copp
    -0.09
    éĢ»
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    ahoma
    -0.09
    æ°¤
    -0.09
    PING
    -0.09
    ç½¾
    -0.08
    èĭŁ
    -0.08
    POSITIVE LOGITS
    اص
    0.09
    5
    0.09
    äºĮåŃĹ
    0.09
    7
    0.09
    3
    0.09
    6
    0.09
    è°ľ
    0.09
    /or
    0.09
    4
    0.08
    å¹ħ度
    0.08
    Activations Density 0.750%

    No Known Activations