© 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. 57699
    Prev
    Next
    INDEX
    Explanations

    from near, from close, from distance

    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
    peg
    -0.09
    èĵ¬
    -0.09
    çıł
    -0.09
    åĽ´çĿĢ
    -0.09
     Fal
    -0.09
    åij½
    -0.09
     incumb
    -0.09
    çļĦä¸Ģ
    -0.09
    ANTS
    -0.08
    奴
    -0.08
    POSITIVE LOGITS
    æ½ľ
    0.10
    éļIJå½¢
    0.10
     недо
    0.09
    èĶº
    0.09
    hab
    0.08
    ä¸įå¼Ģ
    0.08
    家éķ¿ä»¬
    0.08
    箩
    0.08
    讲æķħäºĭ
    0.08
    åī¥å¤º
    0.08
    Activations Density 0.007%

    No Known Activations