© 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. 31486
    Prev
    Next
    INDEX
    Explanations

    infrastructure

    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
    son
    -0.09
    ÑĥÑĤ
    -0.09
    å¿Ŀ
    -0.09
    .liferay
    -0.08
    ikon
    -0.08
    èĪ«
    -0.08
     veto
    -0.08
    éªħ
    -0.08
    ä¾ij
    -0.08
     qed
    -0.08
    POSITIVE LOGITS
    é¾
    0.12
    æĶ¯æĴij
    0.09
     Lent
    0.09
    ä¿Ŀéļľ
    0.09
    urally
    0.09
     dissolution
    0.08
    utral
    0.08
    uve
    0.08
    leased
    0.08
    ctions
    0.08
    Activations Density 0.008%

    No Known Activations