© 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. 39042
    Prev
    Next
    INDEX
    Explanations

    challenges, questions, things, problems

    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
    äºĮåŃĹ
    -0.11
    swith
    -0.10
    ä¸ĢçĤ¹åĦ¿
    -0.10
    ä¸įåģļ
    -0.10
    ä¸Ģ个个
    -0.09
    æİ£
    -0.09
    sWith
    -0.09
    çļĦä¸ĢåĪĩ
    -0.09
    ä¸ĢåŃĹ
    -0.09
    çĤ¹æ»´
    -0.09
    POSITIVE LOGITS
    duk
    0.09
    åĩłä¸ª
    0.08
    صعب
    0.08
    åijĥ
    0.08
     coupe
    0.08
    çĸļ
    0.08
     Ernst
    0.08
    éĺŁéķ¿
    0.08
    0.08
     few
    0.08
    Activations Density 0.242%

    No Known Activations