© 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. 19816
    Prev
    Next
    INDEX
    Explanations

    doesn’t mean

    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
    ä¸į妨
    -0.12
    æĢİä¹Īä¼ļ
    -0.12
    并ä¸įå¤ļ
    -0.10
    å¾Īé«ĺåħ´
    -0.10
    ä¸įæĺ¯å¾Ī
    -0.10
    èĩªçĦ¶èĢĮçĦ¶
    -0.09
    å¾Ī容æĺĵ
    -0.09
    å¾Īéĩįè¦ģçļĦ
    -0.09
    并ä¸į
    -0.09
    æĢİä¹Īåı¯èĥ½
    -0.09
    POSITIVE LOGITS
    å¾ħãģ¡
    0.08
     Dust
    0.08
    èĢ¸
    0.08
     Rena
    0.08
    è¿Ļ两ç§į
    0.08
    asher
    0.08
    ç»ıåİĨè¿ĩ
    0.08
    å°ĺ
    0.08
    æī¬å°ĺ
    0.08
    .persistence
    0.08
    Activations Density 0.043%

    No Known Activations