© 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. 62122
    Prev
    Next
    INDEX
    Explanations

    university or college names

    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
    æ½®
    -0.09
    滩
    -0.08
    angling
    -0.08
    ä¸Ģéĥ¨åĪĨ
    -0.08
    æł¸
    -0.08
    工夫
    -0.08
    ç½ij绾ç§ijæĬĢ
    -0.08
    æ´»åĬĽ
    -0.08
     rever
    -0.08
    èĬľ
    -0.08
    POSITIVE LOGITS
    hung
    0.10
    kits
    0.10
    æĸ¯åĿ¦
    0.09
    æĵįåľº
    0.09
    hop
    0.08
    æĮĤåľ¨
    0.08
    lt
    0.08
    _eg
    0.08
    ryan
    0.08
    íĻĶ
    0.08
    Activations Density 0.068%

    No Known Activations