© 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. 10397
    Prev
    Next
    INDEX
    Explanations

    actor playing a character

    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
    åŀ£
    -0.11
    .Closed
    -0.09
    éªĿ
    -0.09
    祼
    -0.09
    ä¸įèĩ³äºİ
    -0.09
    æŀī
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    ookies
    -0.09
    åĨħ马
    -0.09
    æ¶ĪéĻ¤
    -0.08
    POSITIVE LOGITS
    è§Ĵèī²
    0.11
    çļĦè§Ĵèī²
    0.10
    åIJİæİĴ
    0.09
    role
    0.09
    å¹´é¾Ħ段
    0.09
     courtesy
    0.09
    æĢĢ
    0.09
    Role
    0.09
     role
    0.09
    çĤ¸
    0.08
    Activations Density 0.056%

    No Known Activations