© 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. 7755
    Prev
    Next
    INDEX
    Explanations

    let me know

    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
    åľ¨ä¸Ģèµ·
    -0.09
    åħħåĪĨä½ĵçİ°
    -0.08
    ÑĦикÑģ
    -0.08
    oop
    -0.08
    èĩªæĿ¥
    -0.08
    Promise
    -0.08
    çļĦè¯Ŀé¢ĺ
    -0.08
    已被
    -0.07
    åģļ人
    -0.07
    rones
    -0.07
    POSITIVE LOGITS
    endar
    0.10
    çݳ
    0.10
    è¶ħé«ĺ
    0.09
    è¾ĸ
    0.09
    è¡į
    0.09
    çijģ
    0.09
    uzu
    0.09
     customary
    0.09
    ellan
    0.09
    ichel
    0.08
    Activations Density 0.159%

    No Known Activations