© 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. 22366
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĪĺçģ«
    -0.10
    æµĬ
    -0.10
    å®ŀçī©
    -0.09
    屡
    -0.09
     desp
    -0.09
    èĩªå·±åĸľæ¬¢
    -0.09
    æĬĴ
    -0.09
    èµ·æĿ¥äºĨ
    -0.09
    åĪ«äººçļĦ
    -0.09
    äºĨä¸Ģéģį
    -0.08
    POSITIVE LOGITS
     Evelyn
    0.09
    åĿ¦
    0.08
     ìŀħìŀ¥
    0.08
    æīĭæĦŁ
    0.08
    ä»ĺ
    0.08
    ÙĬÙħØ©
    0.07
    äºĶæĺŁ
    0.07
     Abort
    0.07
    equalTo
    0.07
    .sb
    0.07
    Activations Density 0.000%

    No Known Activations