© 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. 39862
    Prev
    Next
    INDEX
    Explanations

    long periods of time

    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
    å°ģéĿ¢
    -0.08
    iske
    -0.08
     fastest
    -0.08
    rtc
    -0.08
    çļĦæĸĩåŃĹ
    -0.08
    æ¯ıéļĶ
    -0.08
    ä¸ŃéĢĶ
    -0.08
    ä¸Ģå¹´ä¸Ģ度
    -0.08
    ten
    -0.08
    alic
    -0.08
    POSITIVE LOGITS
    å¾Īä¹ħ
    0.19
    å¾Īéķ¿
    0.15
    å¾Īéķ¿æŶéĹ´
    0.14
    éķ¿æŶéĹ´
    0.14
    许ä¹ħ
    0.12
    å·²ä¹ħ
    0.12
    äºĨå¾Īä¹ħ
    0.12
    好ä¹ħ
    0.12
    ä¸Ģ段æŶéĹ´
    0.12
    ä¹ħ
    0.12
    Activations Density 0.083%

    No Known Activations