© 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. 56362
    Prev
    Next
    INDEX
    Explanations

    code paths and identifiers

    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
    ç´¯äºĨ
    -0.09
    lem
    -0.09
    ç½IJ
    -0.08
    ç½ijåĿĢ
    -0.08
    家ä½ı
    -0.08
    èĵ¼
    -0.08
    éļ¾åħ³
    -0.08
    emes
    -0.08
    é¹°
    -0.08
    ç³ĸæŀľ
    -0.08
    POSITIVE LOGITS
    å»ĵ
    0.11
    æľ´ç´ł
    0.09
     ext
    0.09
    ALE
    0.08
    åij¤
    0.08
     darn
    0.08
    acic
    0.08
    Crud
    0.08
    åijµ
    0.08
    اÙĪÙĬØ©
    0.08
    Activations Density 1.005%

    No Known Activations