© 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. 54972
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

    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
    adam
    -0.10
    æľīç§į
    -0.09
    é¼ł
    -0.09
    类产åĵģ
    -0.09
    eel
    -0.08
    æ¨Ĭ
    -0.08
    æİĮæı¡äºĨ
    -0.08
     own
    -0.08
    éĻµ
    -0.08
    olid
    -0.07
    POSITIVE LOGITS
    etta
    0.11
    令人
    0.10
    çľĭä¸Ĭåİ»
    0.10
     nâ
    0.10
    å¤ĸåľ°
    0.09
    æĥ
    0.09
     OST
    0.09
    yte
    0.09
    åĪ°æľĢåIJİ
    0.09
    QRST
    0.09
    Activations Density 0.201%

    No Known Activations