© 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. 47929
    Prev
    Next
    INDEX
    Explanations

    FBI director investigations

    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
     Kirby
    -0.09
    edList
    -0.08
    amily
    -0.08
    人éĹ´
    -0.08
    ä¹Łä¸įæķ¢
    -0.08
     Geoff
    -0.08
    bak
    -0.08
    èĩ¾
    -0.08
    į
    -0.08
    ä¹Łæĺ¯éĿŀ常
    -0.08
    POSITIVE LOGITS
    é«Ń
    0.10
    åĵ¡
    0.10
    æ¾Ħæ¸ħ
    0.10
    æĢ¥
    0.10
    å±Ģéķ¿
    0.09
    ainment
    0.09
    åİĭåĪ¶
    0.09
    á»ĩp
    0.09
    涯
    0.09
    ente
    0.09
    Activations Density 0.006%

    No Known Activations