© 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. 38676
    Prev
    Next
    INDEX
    Explanations

    quarterback names

    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
    ed
    -0.09
    em
    -0.09
    åĪ«çļĦ
    -0.08
    佯
    -0.08
    æ¢ĵ
    -0.08
    驼
    -0.08
    å¾Ĺ罪
    -0.07
    èĢģ头
    -0.07
    spy
    -0.07
    spb
    -0.07
    POSITIVE LOGITS
     Ñģобой
    0.10
     Buch
    0.10
    IBUT
    0.10
     cú
    0.09
    aniu
    0.09
    FRING
    0.09
    èĩ
    0.09
    IONS
    0.09
    ä¸įåľ¨
    0.09
    جز
    0.09
    Activations Density 0.002%

    No Known Activations