© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6942
    Prev
    Next
    INDEX
    Explanations

    locations of events

    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
    ÑĤай
    -0.09
     Loy
    -0.09
    å±ĭ
    -0.08
    åĬ¨çī©åĽŃ
    -0.08
    ourn
    -0.08
    ivant
    -0.08
    anel
    -0.08
    æľ¬ç½ij
    -0.08
    ä¸įå®Į
    -0.08
    CAA
    -0.07
    POSITIVE LOGITS
    SID
    0.09
    æľīéĻIJ责任
    0.09
    arked
    0.09
    æľīåºı
    0.09
    设置äºĨ
    0.08
    éŨåīį
    0.08
    åĨħãģ§
    0.08
     اÙĦتابعة
    0.08
    综èīº
    0.08
    çł
    0.08
    Activations Density 0.050%

    No Known Activations