© 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. 23821
    Prev
    Next
    INDEX
    Explanations

    apply knowledge and practices

    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
    æīģ
    -0.10
    å¤ļåĬŁèĥ½
    -0.09
    èĬ±å¼Ģ
    -0.09
    ä¸ŃåĽ½å¤§éĻĨ
    -0.08
    è´£
    -0.08
    è·ŁçĿĢ
    -0.08
     доÑģÑĤÑĥп
    -0.08
    éļıä¹ĭ
    -0.08
    çijķ
    -0.08
    å½ĵä¹ĭ
    -0.08
    POSITIVE LOGITS
    åºĶçĶ¨äºİ
    0.16
     apply
    0.15
    åºĶçĶ¨
    0.15
    apply
    0.14
     APPLY
    0.14
     applying
    0.14
     applies
    0.14
    _apply
    0.14
     aplic
    0.13
     ìłģìļ©
    0.13
    Activations Density 0.057%

    No Known Activations