© 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. 10879
    Prev
    Next
    INDEX
    Explanations

    link party, url, web

    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
    æ»´æ»´
    -0.10
    è¿Ļ份
    -0.10
    å±Ĥåĩº
    -0.09
    STRU
    -0.09
    没æĶ¶
    -0.09
    ราà¸Ĭà¸ģาร
    -0.09
    æĻ®éĢļ人
    -0.09
    çĿĢä»ĸ
    -0.09
    份
    -0.09
    borough
    -0.09
    POSITIVE LOGITS
    åĨįä¸Ģ次
    0.09
     Exc
    0.09
    exc
    0.09
    éĽī
    0.09
    åħ´å¥ĭ
    0.09
    vely
    0.08
    .exc
    0.08
    åķľ
    0.08
    æݧ
    0.08
    itzer
    0.08
    Activations Density 0.134%

    No Known Activations