© 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. 34937
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    å®īåħ¨æĦŁ
    -0.09
    ighter
    -0.09
    æ¯ĶåĪ©
    -0.09
    ä¸Ģ个éĹ®é¢ĺ
    -0.09
    æĽ´å¤ļä¿¡æģ¯
    -0.09
    æ¯Ķäºļ
    -0.09
    å½ĵä¹ĭ
    -0.09
    èı½
    -0.09
    åħ¨æĹ¥
    -0.09
    æĽ´æ·±
    -0.09
    POSITIVE LOGITS
    CDC
    0.09
    ien
    0.08
    ä¼Łå¤§çļĦ
    0.08
    actor
    0.07
    ember
    0.07
    ald
    0.07
    CORD
    0.07
    enstein
    0.07
    ondo
    0.07
    stry
    0.07
    Activations Density 0.233%

    No Known Activations