© 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. 39402
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun + noun

    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
    åĪĨä¼ļ
    -0.10
    otti
    -0.10
    å±ĢéĿ¢
    -0.09
    åĸŁ
    -0.09
    çļĦå±ĢéĿ¢
    -0.08
    æ½Ń
    -0.08
    vero
    -0.08
     вÑģÑıк
    -0.08
    ATAB
    -0.08
    顺德
    -0.08
    POSITIVE LOGITS
    екÑĤ
    0.09
    主导
    0.09
    å¼±çĤ¹
    0.08
    erval
    0.08
    éĥ½æĹłæ³ķ
    0.08
    马ä¸Ĭ
    0.08
    erable
    0.08
    sters
    0.08
    é«Ģ
    0.08
    ä½İä¸ĭ
    0.08
    Activations Density 0.283%

    No Known Activations