© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21900
    Prev
    Next
    INDEX
    Explanations

    transmission and gearbox mechanics

    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
    haft
    -0.09
    çĶ¬
    -0.09
    ä¸Ģç«Ļ
    -0.09
    å¾Ĺèµ·
    -0.09
    orts
    -0.09
    å¾ĹäºĨ
    -0.09
    .toolbar
    -0.09
    å°ıé¢Ŀ
    -0.09
    avis
    -0.09
    arest
    -0.08
    POSITIVE LOGITS
    ooks
    0.09
     hã
    0.09
    ook
    0.09
    æľºåĬ¨
    0.08
    .Blue
    0.08
    à¹Ģà¸ļา
    0.08
    à¸Ĺà¸Ńà¸Ķ
    0.08
    涩
    0.08
    SCR
    0.08
     Mech
    0.08
    Activations Density 0.023%

    No Known Activations