© 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. 48201
    Prev
    Next
    INDEX
    Explanations

    artworks and artists

    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
    æIJŃ
    -0.09
    chg
    -0.09
    orf
    -0.09
    shaw
    -0.09
    ç²īå°ĺ
    -0.09
    á»ĵ
    -0.08
    æ®·
    -0.08
    éĤª
    -0.08
    dance
    -0.08
    éŃħ
    -0.08
    POSITIVE LOGITS
    è¡Ĺ
    0.10
    æ¿ĢåĬ±
    0.09
    ä¸ĸçķĮ级
    0.09
    夫
    0.09
    è¡ĹåĮº
    0.09
     sore
    0.09
    è¿ĩå¤ļ
    0.08
    ÑĩеÑĤ
    0.08
    è¡Ĺéģĵ
    0.08
    缮åīįåĽ½åĨħ
    0.08
    Activations Density 0.033%

    No Known Activations