© 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. 49415
    Prev
    Next
    INDEX
    Explanations

    what [subject] say

    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
    嵬
    -0.10
    æ¯ıéĢ¢
    -0.09
    ORE
    -0.09
    æİīäºĨ
    -0.09
     Benefit
    -0.09
     Pot
    -0.08
    è´µ
    -0.08
    åĸĺ
    -0.08
    hea
    -0.08
    Thunk
    -0.08
    POSITIVE LOGITS
    说äºĨ
    0.17
    说åĩºæĿ¥
    0.15
    说ä»Ģä¹Ī
    0.14
    说è¿ĩ
    0.14
    对æĪij说
    0.13
    éĥ½è¯´
    0.12
    她说
    0.12
    è¦ģ说
    0.12
    说éģĵ
    0.12
    .say
    0.11
    Activations Density 0.063%

    No Known Activations