© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36387
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by conjunction or start of sentence

    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
    è£
    -0.09
    enan
    -0.09
    alf
    -0.08
    çļĦæķ°éĩı
    -0.08
     Ø¥ÙĨÙĩ
    -0.08
    CHA
    -0.08
    æĬ¢
    -0.08
     formerly
    -0.08
    æĹ¥å¸¸å·¥ä½ľ
    -0.08
    åıijæĺİ
    -0.08
    POSITIVE LOGITS
    /non
    0.10
    诲
    0.10
    éĶĢ
    0.09
    æĦıåij³çĿĢ
    0.09
    çĽ¸äº²
    0.09
    ä¸İåIJ¦
    0.09
    è¿ĻæĦıåij³çĿĢ
    0.09
    ä»Ģä¹ĪæĦıæĢĿ
    0.08
    parm
    0.08
     PIE
    0.08
    Activations Density 0.439%

    No Known Activations