© 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. 4887
    Prev
    Next
    INDEX
    Explanations

    Academy of Sciences members

    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
    åħ¨æ°ijåģ¥èº«
    -0.09
    åĬłå¿«åıijå±ķ
    -0.09
    éĿ©
    -0.09
    åŀĽ
    -0.08
    éĥ¡
    -0.08
    è¿Ļä¹Īå¤ļå¹´
    -0.08
    æīĭ段
    -0.08
     bolt
    -0.08
    建åįİ
    -0.08
    æĮĩçĿĢ
    -0.08
    POSITIVE LOGITS
    éĻ¢å£«
    0.11
    ç§ijåѦéĻ¢
    0.10
    éĻ¢éĻ¢å£«
    0.10
     наÑĥк
    0.10
    inium
    0.09
     memberships
    0.09
     اÙĦÙħÙĦÙĥ
    0.09
    ä¼ļåijĺ
    0.09
     íļĮìĽIJ
    0.09
    Ñģен
    0.09
    Activations Density 0.058%

    No Known Activations