© 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. 31453
    Prev
    Next
    INDEX
    Explanations

    Fitbit, Jami Nord, Disney

    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·
    -0.11
    idan
    -0.11
    åŃ
    -0.10
    æijĶåĢĴ
    -0.10
    æīĵæŀ¶
    -0.10
    ä¸ĭ车
    -0.10
    å·§åIJĪ
    -0.10
     اÙĦÙĦا
    -0.10
    наÑĤ
    -0.10
    æĭį
    -0.10
    POSITIVE LOGITS
    æľŁéĹ´
    0.09
    æī¿åıĹ
    0.08
    0.08
     (
    0.08
    å¤ļãģĦ
    0.08
     nearest
    0.07
     Lyons
    0.07
    饴
    0.07
     closest
    0.07
    ields
    0.07
    Activations Density 0.003%

    No Known Activations