© 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. 4065
    Prev
    Next
    INDEX
    Explanations

    in [locations, descriptions, articles]

    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
    èµĺ
    -0.11
    çļĦä¹IJ趣
    -0.10
    rid
    -0.09
    åĹ£
    -0.09
    rons
    -0.09
    å©Ĭ
    -0.09
    æµģ浪
    -0.09
    éĹ¹
    -0.09
    èıĬ
    -0.09
    æ»ĭåij³
    -0.09
    POSITIVE LOGITS
    è¡£
    0.16
    è¡£æľį
    0.11
    æľįè£ħ
    0.11
     dress
    0.11
    ç©¿æĪ´
    0.11
     attire
    0.11
    çĻ½è¡£
    0.10
    æīĵæī®
    0.10
    ç©¿çĿĢ
    0.10
     одеж
    0.10
    Activations Density 0.054%

    No Known Activations