© 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. 54226
    Prev
    Next
    INDEX
    Explanations

    run by / operated by

    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¿ĻéĩĮæĺ¯
    -0.09
    ارة
    -0.09
     бÑĭ
    -0.09
    åŁºç¡Ģä¸Ĭ
    -0.09
    è°ģèĥ½
    -0.09
    çļĦçľ¼ç¥ŀ
    -0.09
    enc
    -0.08
    led
    -0.08
    ipple
    -0.08
    atcher
    -0.08
    POSITIVE LOGITS
    è¿Ķ
    0.09
     individuals
    0.09
    éĿ
    0.09
    éľı
    0.08
    icking
    0.08
    aac
    0.08
    зав
    0.08
    æ¥Ń
    0.08
    adr
    0.08
    ondo
    0.08
    Activations Density 0.066%

    No Known Activations