© 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. 4206
    Prev
    Next
    INDEX
    Explanations

    times with am/pm or GMT

    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
    èĪ«
    -0.10
    ä¸įçIJĨ
    -0.10
    ä¸ĬåįĬå¹´
    -0.10
    hiro
    -0.09
    寥
    -0.09
    ä¸īçŃīå¥ĸ
    -0.09
    驾çħ§
    -0.09
    ä»Ĭ年以æĿ¥
    -0.09
     |_|
    -0.09
    被è¯Ħ为
    -0.09
    POSITIVE LOGITS
    æľ¬åľ°
    0.12
     local
    0.10
    å½ĵåľ°
    0.09
    åħĪè¡Į
    0.09
    local
    0.09
    åIJ¯
    0.09
    åľ¨å½ĵåľ°
    0.09
    etch
    0.09
    utc
    0.09
     GMT
    0.08
    Activations Density 0.055%

    No Known Activations