© 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. 35857
    Prev
    Next
    INDEX
    Explanations

    places where people come

    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¿ĺ以为
    -0.10
    éĩįéĩį
    -0.10
    èĪĨ
    -0.09
     EÄŁ
    -0.09
    å°ıçĻ½
    -0.09
    ycop
    -0.09
    æĺ¯ä¸Ģä½į
    -0.09
     cấp
    -0.09
    æĻĵå¾Ĺ
    -0.09
    æĹħè¡Į社
    -0.09
    POSITIVE LOGITS
    æĹ¢åı¯ä»¥
    0.09
    躲éģ¿
    0.09
     interrog
    0.09
    æĥ©
    0.09
    çľĭ书
    0.08
    ä¸įèµ·
    0.08
     ger
    0.08
    åĩŃ
    0.08
    åĸĺ
    0.08
    éªij士
    0.08
    Activations Density 0.075%

    No Known Activations