© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10816
    Prev
    Next
    INDEX
    Explanations

    spent time and resources

    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
    è¶ģçĿĢ
    -0.10
    æīĭä¸Ń
    -0.10
    æĺ¯ä¸Ģ件
    -0.10
    otron
    -0.09
    owi
    -0.09
     pace
    -0.09
    è¿Ŀæ³ķè¿Ŀè§Ħ
    -0.09
     ëĪĦ
    -0.09
    hip
    -0.09
    æīĢæıIJä¾ĽçļĦ
    -0.09
    POSITIVE LOGITS
     devoted
    0.14
     spent
    0.12
    çĶ¨æĿ¥
    0.12
    èĩ´åĬĽäºİ
    0.12
    spent
    0.11
    ä¸ĵ注äºİ
    0.11
    æĬķåħ¥åĪ°
    0.11
    主è¦ģçĶ¨äºİ
    0.10
    çĶ¨äºİ
    0.10
     dedicated
    0.10
    Activations Density 0.080%

    No Known Activations