© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36204
    Prev
    Next
    INDEX
    Explanations

    performing analysis, queries, or exercises

    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
    chet
    -0.10
    heck
    -0.09
    éļ¾å¾Ĺ
    -0.09
    éķ§
    -0.09
    便äºİ
    -0.09
    ä»Ģä¹Īåľ°æĸ¹
    -0.08
    nt
    -0.08
    èī³
    -0.08
    æľĪæľ«
    -0.08
    Heading
    -0.08
    POSITIVE LOGITS
    ze
    0.11
    izens
    0.09
    iazza
    0.09
     MOT
    0.09
     chalk
    0.09
    emens
    0.09
    getti
    0.09
    åĩĨå¤ĩå·¥ä½ľ
    0.09
    åľ¨éĩĮéĿ¢
    0.09
    isch
    0.08
    Activations Density 0.225%

    No Known Activations