© 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. 57063
    Prev
    Next
    INDEX
    Explanations

    facts and case facts

    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
    æīĭ段
    -0.11
    è¿Ļ份
    -0.10
    好äºĨ
    -0.09
    uese
    -0.09
    ä¸Ģ份
    -0.09
    quets
    -0.09
    çĶŁæ´»æĸ¹å¼ı
    -0.09
    æķĪèĥ½
    -0.09
    åĴ¦
    -0.09
    æīĺ管
    -0.09
    POSITIVE LOGITS
    éĢĤçĶ¨
    0.09
    çİ°æľī
    0.09
     facts
    0.09
    æľ¬æ¡Ī
    0.09
    æ¡Ī
    0.09
    åıªå¾Ĺ
    0.08
    æ¡Ī件
    0.08
    æ¡Īä¾ĭ
    0.08
    _scenario
    0.08
     applic
    0.08
    Activations Density 0.103%

    No Known Activations