© 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. 31357
    Prev
    Next
    INDEX
    Explanations

    responded by, accomplished by, accelerate reactions

    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
    åįĥéĩĮ
    -0.09
    udy
    -0.09
    éļıçĿĢ
    -0.08
    座ä½į
    -0.08
    åĪ°åºķ
    -0.08
    \Entities
    -0.08
    Obj
    -0.08
    åĮ¹
    -0.08
    æĶ¶æĭ¾
    -0.08
     McB
    -0.08
    POSITIVE LOGITS
     indem
    0.13
     bằng
    0.11
    å§Ĭ
    0.10
     пÑĥÑĤ
    0.10
    鬯
    0.10
    éĿł
    0.09
    举
    0.09
     Aires
    0.09
    åIJĪæł¼
    0.09
    çĨŁ
    0.09
    Activations Density 0.138%

    No Known Activations