© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47432
    Prev
    Next
    INDEX
    Explanations

    possessive forms

    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
    Negative Logits
    agine
    -0.10
    зав
    -0.10
    æĸ°ä¸ĸ纪
    -0.10
    ÃľN
    -0.09
    \Bridge
    -0.09
    неÑģ
    -0.09
    aces
    -0.09
    alink
    -0.09
    _MT
    -0.09
    _MM
    -0.09
    POSITIVE LOGITS
    微信åħ¬ä¼Ĺ
    0.09
    åĨį度
    0.09
    occo
    0.08
    æŃ¤é¡¹
    0.08
     journeys
    0.08
    æĸ°çļĦ
    0.08
    r
    0.08
    entially
    0.08
    åīij
    0.08
     Dep
    0.07
    Activations Density 0.102%

    No Known Activations