© 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. 11124
    Prev
    Next
    INDEX
    Explanations

    Beth followed by names or places

    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
    -0.10
    廨
    -0.09
    ä¸ŃåĽ½åĪ¶éĢł
    -0.09
    EST
    -0.09
    å·¢
    -0.08
    OFFSET
    -0.08
    ä¸¤å¼ł
    -0.08
     _______,
    -0.08
    ','','
    -0.08
    once
    -0.08
    POSITIVE LOGITS
    ched
    0.10
    noc
    0.09
    ãĤĪãģĨãģª
    0.09
    å¿¡
    0.09
    dur
    0.09
    èĭ£
    0.09
    amine
    0.09
     année
    0.08
    antine
    0.08
    اÙĨا
    0.08
    Activations Density 0.009%

    No Known Activations