© 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. 1877
    Prev
    Next
    INDEX
    Explanations

    mixed unicode characters and english words

    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
    èĩ³æѤ
    -0.08
    è¿Ļæīįæĺ¯
    -0.08
     Broadcasting
    -0.08
    æĻģ
    -0.07
    æ´ŀ
    -0.07
     inv
    -0.07
    æµĵæµĵ
    -0.07
    å±±åºĦ
    -0.07
    è¿Ļ份
    -0.07
    imum
    -0.07
    POSITIVE LOGITS
    æ¬ł
    0.10
    æĤ¬æĮĤ
    0.08
    cie
    0.08
    æĹ©æľŁ
    0.08
    èĽ±
    0.07
    夫
    0.07
    locals
    0.07
     padd
    0.07
    itr
    0.07
    flate
    0.07
    Activations Density 0.110%

    No Known Activations