© 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. 11584
    Prev
    Next
    INDEX
    Explanations

    assistance, aid, help, or tools

    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
    æ·±å¤Ħ
    -0.10
    深交
    -0.09
    äºĨä¸Ģåľº
    -0.08
     меÑģÑĤо
    -0.08
    é¦ĺ
    -0.08
    aska
    -0.08
    iska
    -0.08
    alse
    -0.08
    è¡ħ
    -0.08
    iesta
    -0.08
    POSITIVE LOGITS
    è¾ħåĬ©
    0.20
    çļĦ帮åĬ©ä¸ĭ
    0.13
     assistance
    0.13
    è¼Ķ
    0.12
    帮å¿Ļ
    0.12
     assist
    0.12
     aid
    0.12
     trợ
    0.12
    çļĦ帮åĬ©
    0.12
     aids
    0.11
    Activations Density 0.197%

    No Known Activations