© 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. 56428
    Prev
    Next
    INDEX
    Explanations

    size, length, depth, scale, shape, caliber

    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
    tsy
    -0.10
    çıŃåŃIJ
    -0.09
    periment
    -0.09
    ä¸ĢèĪ¬
    -0.09
     Strawberry
    -0.09
    å·¥ä½ľæĸ¹æ¡Ī
    -0.09
    æīĵå¾Ĺ
    -0.09
    調ãģ¹
    -0.09
    æīĢæīĢ
    -0.08
    è¯Ħæ¯Ķ
    -0.08
    POSITIVE LOGITS
     size
    0.14
    ä½ĵéĩı
    0.13
    大å°ı
    0.13
    size
    0.11
    -size
    0.11
    éķ¿åº¦
    0.11
     length
    0.11
    ŀĭ
    0.10
     shape
    0.10
    å½¢çĬ¶
    0.10
    Activations Density 0.279%

    No Known Activations