© 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. 39681
    Prev
    Next
    INDEX
    Explanations

    play video or audio

    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
    å¤±æľĽ
    -0.10
    è²Į
    -0.10
    æĺ¯ä¸Ģ座
    -0.09
    常æĢģåĮĸ
    -0.09
    罡
    -0.09
    avings
    -0.09
    çĶŁäº§åĴĮ
    -0.09
    éĶĢåĶ®æ¸łéģĵ
    -0.09
    .cid
    -0.09
    åIJģ
    -0.08
    POSITIVE LOGITS
     played
    0.09
    çİ©
    0.09
    à¸Ĺà¸Ńà¸ĩ
    0.09
    played
    0.09
    æįī
    0.08
    æݧèĤ¡éĽĨåĽ¢
    0.08
    ç»Īæŀģ
    0.08
    amp
    0.08
    PLAY
    0.08
    (play
    0.08
    Activations Density 0.257%

    No Known Activations