© 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. 49092
    Prev
    Next
    INDEX
    Explanations

    list of

    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
    è··
    -0.10
    ä¸Ģæŀļ
    -0.09
    å°ıåŃIJ
    -0.09
    Focused
    -0.09
    ä¸Ģ个å°ı
    -0.09
    ç±´
    -0.09
     ÙħÙĦÙģ
    -0.09
    åİ¢
    -0.09
    ä¸Ģæŀ¶
    -0.09
    ä¸Ģ款
    -0.09
    POSITIVE LOGITS
    how
    0.10
     WTF
    0.09
    oling
    0.09
    åĢĻ
    0.08
    ä»Ģä¹Īæĺ¯
    0.08
    ä»Ģä¹Īåı«
    0.08
     potential
    0.08
     reasons
    0.08
    icas
    0.08
     events
    0.08
    Activations Density 0.051%

    No Known Activations