© 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. 55229
    Prev
    Next
    INDEX
    Explanations

    quick, simple, smart, luxurious, intense

    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
    nen
    -0.09
    å°±ä¸įèĥ½
    -0.08
    sic
    -0.08
    angan
    -0.08
    为ä¸Ģä½ĵçļĦ
    -0.08
    æĪijéĻ¢
    -0.08
    ä¸įåIJĪæł¼
    -0.08
    æĬµæĬĹåĬĽ
    -0.08
    ä¸ºæł¸å¿ĥçļĦ
    -0.08
    اÙĩÙĦ
    -0.08
    POSITIVE LOGITS
    åıĪ好
    0.10
    ä¸Ķ
    0.10
    ãģĭãģ¤
    0.10
    èĢĮåıĪ
    0.10
    éĢŁåº¦å¿«
    0.09
     yet
    0.09
    erval
    0.09
    åıĪ
    0.09
    DER
    0.09
    yet
    0.08
    Activations Density 0.078%

    No Known Activations