© 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. 36349
    Prev
    Next
    INDEX
    Explanations

    pro- then a word fragment

    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
    еÑĢе
    -0.10
    å¿į
    -0.09
    èįĴ
    -0.08
    åij¼
    -0.08
    åįĩ
    -0.08
    undle
    -0.08
    åįĵ
    -0.08
    ึà¸ģ
    -0.08
    åįĥå¹´
    -0.08
    èĤ©
    -0.08
    POSITIVE LOGITS
    ä¸ĢéĿ¢
    0.15
    æĢģ度
    0.12
    çļĦ姿æĢģ
    0.11
    çļĦä¸ĢéĿ¢
    0.11
    çļĦæĢģ度
    0.11
    åī©ä½Ļ
    0.10
    æ·Ħ
    0.10
    æµ·è¿IJ
    0.10
    çķĻåľ¨
    0.10
    ulatory
    0.09
    Activations Density 0.127%

    No Known Activations