© 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. 18091
    Prev
    Next
    INDEX
    Explanations

    pages and lengths

    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
    åįĥä¸ĩ
    -0.10
    åĩ¡æľ¬ç½ij
    -0.09
    iri
    -0.09
    è¿Ļå¥Ĺ
    -0.08
    ä¸Ģ次次
    -0.08
    éļıçĿĢæŶéĹ´
    -0.08
    æ¯ıä¸Ģ次
    -0.08
     Justi
    -0.08
    毡
    -0.08
    cil
    -0.08
    POSITIVE LOGITS
    æīī
    0.09
    ç¹ģ
    0.09
    .pages
    0.09
    etre
    0.09
    ä¸į失
    0.09
    çķı
    0.09
    amas
    0.08
     pages
    0.08
     loi
    0.08
     conting
    0.08
    Activations Density 0.035%

    No Known Activations