© 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. 3468
    Prev
    Next
    INDEX
    Explanations

    United States, LSD, psychoactive

    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
    abox
    -0.09
    prm
    -0.09
    éĩįå·¥
    -0.08
    HEAD
    -0.08
    lvl
    -0.08
    otype
    -0.08
    marshal
    -0.08
    usz
    -0.08
     puzzles
    -0.08
    .unpack
    -0.08
    POSITIVE LOGITS
    åı£æ°´
    0.11
    让æĤ¨
    0.11
    æľªç»ı
    0.10
    请æĤ¨
    0.10
    é«Ķé©Ĺ
    0.10
    ç¬Ķè¯ķ
    0.10
    åĻİ
    0.09
    éĢĢå¸Ĥ
    0.09
    ç³Ł
    0.09
     takım
    0.09
    Activations Density 0.134%

    No Known Activations