© 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. 57280
    Prev
    Next
    INDEX
    Explanations

    python versions or "as"

    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
    ame
    -0.10
    æŃ£åľ¨è¿Ľè¡Į
    -0.09
    çŁ³æ²¹
    -0.09
    赶
    -0.09
    å·¡åĽŀ
    -0.09
    jid
    -0.09
    åºľ
    -0.08
    inati
    -0.08
    åħħåĪĨåĪ©çĶ¨
    -0.08
    湫
    -0.08
    POSITIVE LOGITS
    ä¸Ģé¢Ĺ
    0.11
    èł
    0.10
    æ²Ļ滩
    0.10
    ä¸Ģé¡¿
    0.09
    ä¸ĢåĽ¢
    0.09
    ãģªãĤĭ
    0.09
    ä¸Ģçīĩ
    0.09
    é«ĺä¸ŃçĶŁ
    0.08
    åī§åľº
    0.08
     cl
    0.08
    Activations Density 0.008%

    No Known Activations