© 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. 55648
    Prev
    Next
    INDEX
    Explanations

    mind's inner workings

    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
    åħ±åIJĮä½ĵ
    -0.09
    å½Ŀ
    -0.09
     tales
    -0.09
    emain
    -0.08
    éĺ¶
    -0.08
    ä¸ĢåŃĹ
    -0.08
    ès
    -0.08
    à¹Ģสมà¸Ń
    -0.07
     distrib
    -0.07
    pto
    -0.07
    POSITIVE LOGITS
    reve
    0.11
    blings
    0.10
    æ·±å¤Ħ
    0.10
    FM
    0.09
    èĬĻ
    0.09
     thoughts
    0.09
    åįİ缼
    0.09
     Äijiá»ĥn
    0.09
    è°ģçŁ¥
    0.09
     inner
    0.09
    Activations Density 0.043%

    No Known Activations