© 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. 50247
    Prev
    Next
    INDEX
    Explanations

    not available or out

    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
    rlen
    -0.10
    ä»»ä½ķå½¢å¼ı
    -0.09
    ä¾ij
    -0.09
     âĸij
    -0.09
    els
    -0.09
    zy
    -0.08
    å²Ķ
    -0.08
    åħ¥åºĵ
    -0.08
    åħ¬ç½ij
    -0.08
    ç¿®
    -0.08
    POSITIVE LOGITS
    anna
    0.11
    åľ°åĮº
    0.10
    ç»ĦåIJĪ
    0.09
    åĴĮåľ°åĮº
    0.09
    éĥ¨åĪĨåľ°åĮº
    0.09
    ãģĹãģĭ
    0.09
    满
    0.08
    并ä¸į代表
    0.08
    åıªå¥½
    0.08
    åı¯ä¾Ľ
    0.08
    Activations Density 0.060%

    No Known Activations