© 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. 30055
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    è¯ķ
    -0.11
    _CAST
    -0.09
    å»Ĭ
    -0.09
    æĨĭ
    -0.09
    éĻħ
    -0.09
    azen
    -0.08
    æľ¬èĥ½
    -0.08
    ç²¥
    -0.08
    _TestCase
    -0.08
    ä¼ģ
    -0.08
    POSITIVE LOGITS
     extrapol
    0.09
    åľ¨æĪijçļĦ
    0.09
    å°Ĩ以
    0.09
    è¿Ļ项
    0.09
     Ñģмог
    0.09
    æīĭæĮģ
    0.09
    ptive
    0.09
    åľ¨ä»ĸçļĦ
    0.09
    ynn
    0.08
    è¶³å¤Ł
    0.08
    Activations Density 0.090%

    No Known Activations