© 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. 53589
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
    æıIJæĮ¯
    -0.10
    缮æłĩä»»åĬ¡
    -0.10
    RING
    -0.09
    å®ŀçī©
    -0.09
    å¥ĸéĩij
    -0.09
    èĢģ大
    -0.09
    åħ¨éĿ¢å»ºæĪIJ
    -0.09
    è´»
    -0.09
    æIJŀ好
    -0.09
    cé
    -0.09
    POSITIVE LOGITS
     Äijá»ĥ
    0.14
     ÑĩÑĤобÑĭ
    0.13
    为äºĨ
    0.12
     pour
    0.12
    çĤºäºĨ
    0.11
    以便
    0.11
    æĿ¥
    0.11
     untuk
    0.10
     inorder
    0.10
    æĿ¥åģļ
    0.10
    Activations Density 0.487%

    No Known Activations