© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35757
    Prev
    Next
    INDEX
    Explanations

    come a long way

    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
    æ´¥
    -0.09
    祯
    -0.09
    声åĵį
    -0.09
    罪
    -0.09
     Wing
    -0.08
    æIJ
    -0.08
    ç½
    -0.08
    èĭ±æł¼
    -0.08
    æĮļ
    -0.08
    çĻĸ
    -0.08
    POSITIVE LOGITS
    æĹħç¨ĭ
    0.14
     journey
    0.14
    æĹħéĢĶ
    0.13
    jour
    0.13
    ä¸įæĺĵ
    0.12
    è·¯ç¨ĭ
    0.12
    è¡Įç¨ĭ
    0.12
    åİĨç¨ĭ
    0.12
    åľ¨è·¯ä¸Ĭ
    0.11
    å¾Īéķ¿
    0.11
    Activations Density 0.045%

    No Known Activations