© 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. 11044
    Prev
    Next
    INDEX
    Explanations

    "case of"

    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
    èĤī
    -0.11
    çļĦæ¨¡æł·
    -0.10
    åįģä¸ĩ
    -0.10
    对åħ¶è¿Ľè¡Į
    -0.10
    çīł
    -0.10
    çļĦéĩįçĤ¹
    -0.09
    éĩįçĤ¹
    -0.09
    æ¹ĸæ³Ĭ
    -0.09
    éĺ
    -0.09
    herits
    -0.09
    POSITIVE LOGITS
     ours
    0.16
    æľ¬æ¡Ī
    0.14
    ä½ķåĨµ
    0.13
    è¿Ļ次
    0.13
     yours
    0.13
    ours
    0.12
     hers
    0.12
    éĢĻ次
    0.12
    æŃ¤æ¬¡
    0.11
    æľ¬æ¬¡
    0.11
    Activations Density 0.155%

    No Known Activations