© 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. 22060
    Prev
    Next
    INDEX
    Explanations

    fuel economy and battery life

    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
    æĽ¿
    -0.11
    oda
    -0.11
    èĥ¸
    -0.10
    çŀ§
    -0.10
    et
    -0.09
    etti
    -0.09
    (es
    -0.09
    รà¸Ńà¸ĩ
    -0.09
    æĶ¾å¼ĥ
    -0.09
    ä¾ĽçĥŃ
    -0.09
    POSITIVE LOGITS
    æĿª
    0.10
    æĢ§åĴĮ
    0.10
    rens
    0.08
    à¹ģละà¸Ħวาม
    0.08
     ÑĢежим
    0.08
    zza
    0.08
    æĸ°æĺ¥
    0.08
    ç®ķ
    0.08
    åıĪ好
    0.08
    tant
    0.08
    Activations Density 0.030%

    No Known Activations