© 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. 54020
    Prev
    Next
    INDEX
    Explanations

    reissue and restoration

    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
    uar
    -0.09
    ç§ijæĬĢåĽŃ
    -0.09
    åĢĻ
    -0.09
    SOR
    -0.09
    æł½
    -0.09
    è¦ģéĹ»
    -0.09
    ignant
    -0.09
    apos
    -0.08
     NTN
    -0.08
    éĴ¥
    -0.08
    POSITIVE LOGITS
    éĩį温
    0.11
    è¿Ļä¹Īå¤ļå¹´
    0.11
    éĩįçİ°
    0.10
    礼åĮħ
    0.10
     Classics
    0.10
    æ»ĭåħ»
    0.10
    ç»ıåħ¸
    0.09
    æĬ¢æķij
    0.09
    导读
    0.09
    æŶéļĶ
    0.09
    Activations Density 0.132%

    No Known Activations