© 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. 5445
    Prev
    Next
    INDEX
    Explanations

    financial and academic support

    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
    åīįä¸Ģ天
    -0.09
    æŬ
    -0.09
    ä¸įå¾Ĺ转载
    -0.09
    IMS
    -0.09
    å·¡åĽŀ
    -0.09
    çĭ¬ç«ĭèij£äºĭ
    -0.09
    oter
    -0.08
     ValidationResult
    -0.08
    çŃIJ
    -0.08
    éķ¿éĢĶ
    -0.08
    POSITIVE LOGITS
    ä¼ĺæĥłæĶ¿çŃĸ
    0.09
    æİĸ
    0.09
    pta
    0.09
    è¯Ħ论
    0.09
    nesc
    0.09
    æĬ¹
    0.09
    -leg
    0.09
    çļĦç¡®
    0.09
     Avery
    0.08
    agy
    0.08
    Activations Density 0.075%

    No Known Activations