© 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. 38047
    Prev
    Next
    INDEX
    Explanations

    maintain something

    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¸įå¦Ĥ
    -0.09
    icolor
    -0.09
    å·¨åŀĭ
    -0.09
    æľīå¾ħ
    -0.09
    ulous
    -0.09
    åIJĮæĹ¶ä¹Ł
    -0.08
     Thế
    -0.08
    athy
    -0.08
    èĬ±éĴ±
    -0.08
    jan
    -0.08
    POSITIVE LOGITS
    èѦæĥķ
    0.10
    ä¸Ģå®ļçļĦ
    0.10
    ä¸Ģåī¯
    0.10
    对èĩªå·±çļĦ
    0.09
    AspectRatio
    0.09
    ä½£
    0.09
    åĩłåĪĨ
    0.09
    ance
    0.09
     focus
    0.09
    çĻ¾åĪĨä¹ĭ
    0.08
    Activations Density 0.024%

    No Known Activations