© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24333
    Prev
    Next
    INDEX
    Explanations

    unt-related prefixes

    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
    Negative Logits
    íıIJ
    -0.12
    antine
    -0.10
    sing
    -0.09
    ses
    -0.09
    ä¸įçķĻ
    -0.09
    è¿Ļä¸įæĺ¯
    -0.09
     Williamson
    -0.08
    .assets
    -0.08
    峪
    -0.08
    ÑĨион
    -0.08
    POSITIVE LOGITS
    ted
    0.11
    ting
    0.10
    itled
    0.10
    çĦ¶æĺ¯
    0.10
    رÙĬ
    0.10
    elope
    0.10
    rent
    0.09
    reat
    0.09
    imately
    0.09
    æ·±å¤Ħ
    0.09
    Activations Density 0.010%

    No Known Activations