© 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. 61705
    Prev
    Next
    INDEX
    Explanations

    write about

    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
    éĺħè§Ī
    -0.09
    pard
    -0.09
    iras
    -0.08
    èµŃ
    -0.08
    çİ©ç¬ij
    -0.08
    æĥħåĨµä¸ĭ
    -0.08
    éĴĪ对
    -0.08
    çĸı
    -0.08
    æľīçļĦ
    -0.08
    åı£è¯Ń
    -0.08
    POSITIVE LOGITS
    çļĦè¯Ŀé¢ĺ
    0.10
     topics
    0.10
    anything
    0.10
    subjects
    0.10
    åĴĮæľįåĬ¡
    0.10
     subjects
    0.10
    æ¯įæł¡
    0.09
    åĬ¡
    0.09
    家乡
    0.09
    æŃ¦ä¾ł
    0.09
    Activations Density 0.050%

    No Known Activations