© 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. 22848
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    å±ıå¹ķä¸Ĭ
    -0.10
     itself
    -0.10
    æĪijçļĦå¿ĥ
    -0.09
    -minded
    -0.09
     themselves
    -0.09
    å®ĥ们
    -0.09
    èĬľ
    -0.09
    led
    -0.08
    çĿĢä»ĸ
    -0.08
    å¼ĢåıijåĮº
    -0.08
    POSITIVE LOGITS
    /her
    0.23
    /th
    0.13
    zelf
    0.13
    -même
    0.12
    /us
    0.11
    SELF
    0.11
    èĢģ人家
    0.10
    /the
    0.10
    çļĦ羣å®ŀ
    0.10
     gái
    0.09
    Activations Density 0.236%

    No Known Activations