© 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. 37567
    Prev
    Next
    INDEX
    Explanations

    caution and carefulness

    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
    à¹īà¸Ńย
    -0.09
    åıŁ
    -0.09
     кÑĥлÑĮÑĤÑĥÑĢÑĭ
    -0.09
    èĻ±
    -0.09
    lash
    -0.09
    å¿ĥåĬ¨
    -0.09
    Ñħо
    -0.09
    驾
    -0.09
     зÑĢ
    -0.09
    å®īåħ¨æĦŁ
    -0.08
    POSITIVE LOGITS
    æݪ
    0.10
    è¡Įäºĭ
    0.09
    wy
    0.09
    ä¸įè¦ģ
    0.09
    _MED
    0.08
     mạch
    0.08
    åĭ¿
    0.08
    ness
    0.08
    è¿ĻéĩĮçļĦ
    0.08
    è¨Ģè¡Į
    0.08
    Activations Density 0.007%

    No Known Activations