© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59055
    Prev
    Next
    INDEX
    Explanations

    phones, tablets, devices

    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
    çŀª
    -0.10
    RIA
    -0.10
    èĥ¡åŃIJ
    -0.09
    继ç»Ńä¿ĿæĮģ
    -0.09
    河西
    -0.09
    æ¨Ĺ
    -0.08
    æĿŀ
    -0.08
    æĥ³èµ·äºĨ
    -0.08
    é¼ĵèĪŀ
    -0.08
    è·Ĩ
    -0.08
    POSITIVE LOGITS
    æīĭæľº
    0.15
    å¹³æĿ¿
    0.14
     phones
    0.13
    çĶµèĦij
    0.13
     devices
    0.12
    ç¬Ķè®°æľ¬
    0.12
     computers
    0.12
     smartphones
    0.12
    设å¤ĩ
    0.12
     device
    0.12
    Activations Density 0.229%

    No Known Activations