© 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. 62890
    Prev
    Next
    INDEX
    Explanations

    group or organizational 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
    è¿ĩåħ³
    -0.10
    对ç«ĭ
    -0.10
    éļĶå£ģ
    -0.10
    çĢı覽
    -0.09
    è´¨éĩıéĹ®é¢ĺ
    -0.09
    pisa
    -0.09
    ä¸ĸä¸Ĭ
    -0.09
    豪åįİ
    -0.09
    åİĭ
    -0.09
    åĸ½
    -0.08
    POSITIVE LOGITS
    éŁ³ä¹IJä¼ļ
    0.10
    åĴĴ
    0.09
     Caldwell
    0.09
     Concert
    0.09
    çĪ±å¥½
    0.09
    åĮĻ
    0.09
    ç½²
    0.09
    èĹķ
    0.08
    æĭĺ
    0.08
    inte
    0.08
    Activations Density 0.089%

    No Known Activations