© 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. 35682
    Prev
    Next
    INDEX
    Explanations

    Wikipedia and encyclopedias

    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
    ataires
    -0.10
    éļIJèĶ½
    -0.10
    åIJ¬å¾Ĺ
    -0.09
    æ½ľ
    -0.09
    _functions
    -0.09
    ÑģÑĥд
    -0.09
    виÑĤ
    -0.09
    _FM
    -0.09
    RAL
    -0.09
    ataire
    -0.09
    POSITIVE LOGITS
    çĻ¾ç§ij
    0.15
     Wikipedia
    0.12
    ç»´
    0.11
    .wikipedia
    0.10
     encyclopedia
    0.09
     wikipedia
    0.09
    wiki
    0.09
    Wik
    0.09
    è¦ĨçĽĸéĿ¢
    0.09
    åıĻ
    0.09
    Activations Density 0.047%

    No Known Activations