© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36858
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun

    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
    nyder
    -0.11
    ëģĶ
    -0.10
    ematic
    -0.10
    mate
    -0.10
    /or
    -0.09
    鸷
    -0.09
    APE
    -0.09
    mates
    -0.09
    éĢĨè¡Į
    -0.09
    ernel
    -0.09
    POSITIVE LOGITS
     own
    0.13
     же
    0.12
    ../../../
    0.11
    'e
    0.10
     bè
    0.10
    ists
    0.09
    turn
    0.09
    zelf
    0.09
    ist
    0.09
    untu
    0.09
    Activations Density 0.128%

    No Known Activations