© 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. 50471
    Prev
    Next
    INDEX
    Explanations

    that followed by context

    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
    ãģĿãĤĮãģĮ
    -0.10
     ÑĤомÑĥ
    -0.10
    -0.09
    å°±æĺ¯è¿Ļæł·
    -0.09
    éĤ£å°±
    -0.09
    ãģĿãĤĮ
    -0.09
    abay
    -0.09
    éĤ£äºĽ
    -0.09
    çļĦæķ°æį®
    -0.09
    è¿ĻéĩĮæľī
    -0.09
    POSITIVE LOGITS
    zelf
    0.17
    /th
    0.16
    ched
    0.16
     же
    0.12
    çİ©æĦı
    0.12
    æĻĤåĢĻ
    0.12
     pes
    0.12
     particular
    0.11
    ç±»åŀĭçļĦ
    0.11
    åı¥è¯Ŀ
    0.10
    Activations Density 0.128%

    No Known Activations