© 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. 63586
    Prev
    Next
    INDEX
    Explanations

    that followed by a clause

    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
    ingham
    -0.10
    ç»´å¥ĩ
    -0.08
     اÙĦÙħÙĪا
    -0.08
    coach
    -0.08
    ovi
    -0.08
    åłł
    -0.08
    osg
    -0.08
     Tecn
    -0.08
    éĤ£æ¬¡
    -0.08
    OCUS
    -0.08
    POSITIVE LOGITS
    å¾ĹäºĨ
    0.09
    è¶Ĭæĺ¯
    0.09
    arness
    0.09
    æŃ£æĺ¯åĽłä¸º
    0.08
    åĩ¡äºĭ
    0.08
    gü
    0.08
    dam
    0.08
    ä¹ĭæĦı
    0.08
    ÐĶÐķ
    0.08
    ä¸ĩäºĭ
    0.08
    Activations Density 0.133%

    No Known Activations