© 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. 37752
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
    GMT
    -0.08
    æ¶ī
    -0.08
    mall
    -0.08
    arry
    -0.08
     Winds
    -0.08
    agne
    -0.07
    apon
    -0.07
    udu
    -0.07
    epar
    -0.07
     Wayne
    -0.07
    POSITIVE LOGITS
    第äºĶå±Ĭ
    0.11
    æķijåij½
    0.10
    æIJ¬è¿ģ
    0.10
    èį¥
    0.10
    æīī
    0.10
    å½ĵåľ°äºº
    0.10
    åģļå®Į
    0.10
    ç§ĭ天
    0.10
    åı¯ä»¥è®©
    0.10
    ä¼Ĭæĭī
    0.10
    Activations Density 0.304%

    No Known Activations