© 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. 31039
    Prev
    Next
    INDEX
    Explanations

    variability: climate, weather, oscillations

    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
     Robbins
    -0.10
    Ñģк
    -0.10
    ä¸ĢæĹ¥
    -0.09
    Margins
    -0.09
    rov
    -0.08
    utherford
    -0.08
    å°¼åħĭ
    -0.08
    -anchor
    -0.08
    èĮģ
    -0.08
    èħ¼
    -0.08
    POSITIVE LOGITS
    çĻ¾å¹´
    0.10
    çŃĩ
    0.10
    è¢Ħ
    0.09
    æijĨ
    0.09
    管çIJĨæĿ¡ä¾ĭ
    0.09
    æ±Łæ¹ĸ
    0.09
    Jet
    0.08
     Jets
    0.08
    æģ©æĸ½
    0.08
    鼩
    0.08
    Activations Density 0.050%

    No Known Activations