© 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. 47714
    Prev
    Next
    INDEX
    Explanations

    scope of

    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
    è¸ı
    -0.11
    è¹ĭ
    -0.10
    æĴķ
    -0.09
    iage
    -0.09
    oration
    -0.09
    idge
    -0.09
    æĸŁ
    -0.08
    æīĭä¸Ĭ
    -0.08
    å°Ĭ严
    -0.08
    åĬ¢
    -0.08
    POSITIVE LOGITS
    èĮĥåĽ´
    0.23
     scope
    0.23
    scope
    0.21
     Scope
    0.20
    Scope
    0.19
    .scope
    0.18
    _scope
    0.18
    èĮĥåĽ´åĨħ
    0.18
    (scope
    0.18
    ç¯Ħ
    0.17
    Activations Density 0.160%

    No Known Activations