© 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. 55490
    Prev
    Next
    INDEX
    Explanations

    but not

    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
    çij°
    -0.11
    åĪ«
    -0.10
    åIJĦæĸ¹éĿ¢
    -0.10
    MDB
    -0.10
    æĢĢçĿĢ
    -0.10
    æĤ¬
    -0.09
    åIJĦå¼ı
    -0.09
    çŃīçŃī
    -0.09
    ãģĿãĤĮãģ§ãĤĤ
    -0.09
    fred
    -0.09
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.29
    èĢĮä¸įæĺ¯
    0.27
     rather
    0.21
     not
    0.20
    ãģ§ãģ¯ãģªãģı
    0.20
     chứ
    0.18
     NOT
    0.16
     ÙĪÙĦÙĬس
    0.16
    not
    0.15
    rather
    0.15
    Activations Density 0.090%

    No Known Activations