© 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. 3890
    Prev
    Next
    INDEX
    Explanations

    qualities inherent

    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
    ritch
    -0.09
    ç²¾ç¥ŀçĹħ
    -0.09
    走访
    -0.09
    éŃĶ鬼
    -0.09
     Dayton
    -0.09
    注æĺİåĩºå¤Ħ
    -0.08
    æIJį害
    -0.08
     Fallon
    -0.08
    æĺ¥æĻļ
    -0.08
    æįŁå®³
    -0.08
    POSITIVE LOGITS
    çıŃ级
    0.09
    裤åŃIJ
    0.09
    /topics
    0.08
    олод
    0.08
    æĪijå½ĵæŶ
    0.08
    æŃ£å¥½
    0.08
    家ä¼Ļ
    0.08
    getContent
    0.08
    YS
    0.08
    LOGGER
    0.08
    Activations Density 0.201%

    No Known Activations