© 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. 22901
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    ä¹±
    -0.09
    áĢĴ
    -0.08
    Spacer
    -0.08
    åŁİ乡å±ħæ°ij
    -0.08
    祸
    -0.08
    çĿ£
    -0.08
     devoted
    -0.07
    丹
    -0.07
    éļ¶
    -0.07
    æ¥ł
    -0.07
    POSITIVE LOGITS
    ouses
    0.09
    çĵ®
    0.09
    .hom
    0.09
    æľªæĽ¾
    0.09
    对æĪij们
    0.09
    ТЬ
    0.09
    éĢ¾
    0.09
    ÑĪи
    0.08
     Bek
    0.08
    Vintage
    0.08
    Activations Density 0.020%

    No Known Activations