© 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. 27685
    Prev
    Next
    INDEX
    Explanations

    books, publishers, press, blog, newsletter

    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
    kus
    -0.09
    å¼Ĥåľ°
    -0.09
    bens
    -0.09
    寮
    -0.08
    æĪij们å°Ĩ
    -0.08
    éģĹ
    -0.08
    广大å¸Ĥæ°ij
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    imers
    -0.08
    å½ĵä¹ĭ
    -0.08
    POSITIVE LOGITS
    ypy
    0.09
     Macron
    0.09
    æݨåĩº
    0.09
    çł
    0.09
    Putin
    0.09
    æľīéĻIJ责任
    0.09
     Nicholson
    0.09
    éľİ
    0.09
    åı£
    0.08
    æݨåĩºçļĦ
    0.08
    Activations Density 0.024%

    No Known Activations