© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10202
    Prev
    Next
    INDEX
    Explanations

    chic

    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
    ãģ¹ãģį
    -0.09
     unspecified
    -0.08
    icit
    -0.08
    è¡·
    -0.08
    itive
    -0.08
    iffin
    -0.08
    uncan
    -0.08
    æİ¥éĢģ
    -0.08
    arian
    -0.08
    çī¢
    -0.07
    POSITIVE LOGITS
    è¿Ń
    0.10
    ä¹ĭ举
    0.09
    æ®ī
    0.09
    çİ©æĦı
    0.09
    trl
    0.09
    emu
    0.09
    æĹłäººé©¾é©¶
    0.09
     одеж
    0.09
    åľ°æ®µ
    0.09
    天èĬ±
    0.09
    Activations Density 0.003%

    No Known Activations