© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20458
    Prev
    Next
    INDEX
    Explanations

    blog post website media accounts

    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
    æļ®
    -0.10
    _CONSOLE
    -0.10
    .drag
    -0.09
    ATTER
    -0.09
    ocity
    -0.09
    åį«
    -0.09
     Bey
    -0.09
     Nude
    -0.09
    AGR
    -0.09
    è¡Ľ
    -0.09
    POSITIVE LOGITS
    å©¢
    0.09
    æĥŃ
    0.09
    iful
    0.09
    æ¶Īæģ¯ç§°
    0.09
    äºĨ个
    0.09
    çijķ
    0.08
    派人
    0.08
     Own
    0.08
    éģIJ
    0.08
    æĿī
    0.08
    Activations Density 0.041%

    No Known Activations