© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7871
    Prev
    Next
    INDEX
    Explanations

    one

    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
    /AP
    -0.10
    åī½
    -0.10
    æľīçļĦ
    -0.09
    çªĴ
    -0.09
    æ¥ļ
    -0.09
    dera
    -0.09
     anlam
    -0.09
     èĭ¥è¦ģ
    -0.09
     Few
    -0.09
     некоÑĤоÑĢÑĭе
    -0.09
    POSITIVE LOGITS
     ear
    0.09
    äººåľ¨
    0.09
    ä¸įèµ·
    0.09
     Rout
    0.08
    æ±ĩèģļ
    0.08
    ened
    0.08
    éķĴ
    0.08
    ä¸įåĩº
    0.08
    ene
    0.08
    =====↵
    0.08
    Activations Density 0.075%

    No Known Activations