© 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. 20068
    Prev
    Next
    INDEX
    Explanations

    Rupert, Cupertino, reserved

    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
    è¹ģ
    -0.09
    åĪ¹
    -0.09
    iete
    -0.08
    æijĦå½±ä½ľåĵģ
    -0.08
     bench
    -0.08
    ä¹į
    -0.08
    ctr
    -0.08
    åIJĦåİ¿
    -0.08
    å¹¿åľº
    -0.08
    çļĦçľ¼çĿĽ
    -0.08
    POSITIVE LOGITS
    èī°
    0.09
    åħ¬åı¸çļĦ
    0.09
    ä½İè°ĥ
    0.09
    åŀ£
    0.09
    纳
    0.09
    å®Ĺ
    0.08
    _regular
    0.08
    å¾ĢåIJİ
    0.08
     Ñĩем
    0.08
    æѤåĪ»
    0.08
    Activations Density 0.007%

    No Known Activations