© 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. 23580
    Prev
    Next
    INDEX
    Explanations

    invention of

    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
    ä»°
    -0.10
    ä¹ŁæĪIJ为
    -0.10
    åįı
    -0.10
    èĴ¯
    -0.09
    éĹªçĶµ
    -0.09
    è¿ĩå¾Ĺ
    -0.09
    èIJ¼
    -0.09
    æĶ¶èİ·
    -0.09
    åį«
    -0.09
    èĻij
    -0.09
    POSITIVE LOGITS
    ris
    0.10
    ì§Ī
    0.09
    atty
    0.08
    atte
    0.08
    owered
    0.08
    ä¼ļéķ¿
    0.08
    odos
    0.08
    aras
    0.08
    èģĬ
    0.08
    inos
    0.08
    Activations Density 1.720%

    No Known Activations