© 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. 1225
    Prev
    Next
    INDEX
    Explanations

    and invoke

    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
     ÑıвлÑı
    -0.10
    ìĬ¤íģ¬
    -0.09
    建议
    -0.09
    建èŃ°
    -0.09
    ores
    -0.08
    æī¶è´«å·¥ä½ľ
    -0.08
    еÑģп
    -0.08
    of
    -0.08
     Tot
    -0.08
    ики
    -0.08
    POSITIVE LOGITS
    åģļ大
    0.10
    æİīäºĨ
    0.09
    åIJ®
    0.09
    ä¸Ģè´¯
    0.09
    åĪ°äºĨ
    0.09
    ING
    0.09
    ä½ľ
    0.09
    éĶĻäºĨ
    0.09
    USH
    0.09
    alph
    0.08
    Activations Density 0.305%

    No Known Activations