© 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. 55924
    Prev
    Next
    INDEX
    Explanations

    copyright and rights

    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
    æĻ®éĢļçļĦ
    -0.09
    寻常
    -0.09
    好ä¸į容æĺĵ
    -0.09
    ulp
    -0.09
    ulpt
    -0.09
    çŃ¾ç½²äºĨ
    -0.08
    éĥ¿
    -0.08
     اÙĦØ°
    -0.08
    ë²
    -0.08
     AssemblyProduct
    -0.08
    POSITIVE LOGITS
    éļıæŶ
    0.10
    AKE
    0.09
    éļ¨æĻĤ
    0.09
    ä½ķæŶ
    0.09
    åįĹåĮĹ
    0.09
    è¬ĩ
    0.09
    èij¬
    0.08
    ijing
    0.08
    gable
    0.08
    éļıæŶéļıåľ°
    0.08
    Activations Density 0.009%

    No Known Activations