© 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. 3912
    Prev
    Next
    INDEX
    Explanations

    scene of events

    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
    urd
    -0.09
    è§ĤçĤ¹
    -0.09
    ception
    -0.09
    èĥļ
    -0.09
    ä»İä¸Ń
    -0.08
    è¢Ĥ
    -0.08
    ï½¢
    -0.08
    åĽłä¸ºå®ĥ
    -0.08
     Vad
    -0.08
     negot
    -0.08
    POSITIVE LOGITS
    AndUpdate
    0.09
    å¸ĥ
    0.09
     TP
    0.08
    æŶéĹ´ä¸º
    0.08
    uz
    0.08
    æīĢåľ¨åľ°
    0.08
    æĢİèĥ½
    0.08
    uff
    0.08
    åħµ
    0.08
    agne
    0.08
    Activations Density 0.018%

    No Known Activations