© 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. 50986
    Prev
    Next
    INDEX
    Explanations

    access to commenting, download, documentation

    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
     Circus
    -0.09
    纽
    -0.09
    è½®
    -0.09
    ä¹ĭåĬ¿
    -0.09
    ëį°
    -0.08
    ãģıãĤĮ
    -0.08
    æīĭæľºåı·
    -0.08
    强è¡Į
    -0.08
    论
    -0.08
    _placement
    -0.08
    POSITIVE LOGITS
    oday
    0.10
    å´ĩé«ĺ
    0.09
    åİĨåı²æĢ§
    0.09
    é«ĺè´µ
    0.08
    éĺ´éĺ³
    0.08
    eward
    0.08
    絾
    0.08
    ohan
    0.08
    emme
    0.08
    èĪ«
    0.08
    Activations Density 0.109%

    No Known Activations