© 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. 6622
    Prev
    Next
    INDEX
    Explanations

    possession or ownership

    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
    å½»
    -0.10
    uzzi
    -0.09
    åłµ
    -0.09
     sho
    -0.09
    bare
    -0.08
    裸
    -0.08
    éĥģ
    -0.08
     Sho
    -0.08
    udson
    -0.08
    èĦ¸ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    åı¦
    0.10
    iable
    0.10
     separate
    0.09
    漪
    0.09
    æĮº
    0.09
    å·¥åľ°
    0.09
    ober
    0.08
     stead
    0.08
    åįķçĭ¬
    0.08
     Separate
    0.08
    Activations Density 0.034%

    No Known Activations