© 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. 12080
    Prev
    Next
    INDEX
    Explanations

    arian, arily

    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
    åIJĸ
    -0.09
    olare
    -0.08
    еÑĩа
    -0.08
    å«Įçĸij
    -0.08
    ellar
    -0.08
    emploi
    -0.08
    çijĹ
    -0.08
    ç´ł
    -0.08
    inder
    -0.07
    æŃĨ
    -0.07
    POSITIVE LOGITS
    ÑĢей
    0.09
    çĥ
    0.09
    çŀ§
    0.09
     наÑģÑĤоÑı
    0.08
    å½Ģ
    0.08
    åĩºæīĭ
    0.08
    è¿ŁåĪ°
    0.08
    arily
    0.08
    ãģ¤ãģij
    0.08
    arian
    0.08
    Activations Density 0.048%

    No Known Activations