© 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. 56434
    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
    æĿĥå¨ģ
    -0.10
    ä¼ĹæīĢ
    -0.10
    人æĿĥ
    -0.09
    plode
    -0.09
    pis
    -0.09
    æĹłå½¢
    -0.09
    resco
    -0.09
    hibited
    -0.09
    pei
    -0.09
    æĴĻ
    -0.09
    POSITIVE LOGITS
    idget
    0.08
    åŃIJ女
    0.08
    éľŃ
    0.08
    æŶéĹ´æ®µ
    0.07
     ve
    0.07
    ç¿ģ
    0.07
    çģ«çĤ¬
    0.07
    umni
    0.07
    èĮģ
    0.07
    继æī¿
    0.07
    Activations Density 0.033%

    No Known Activations