© 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. 29652
    Prev
    Next
    INDEX
    Explanations

    individual followed by a noun

    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
    导读
    -0.08
    ÑģÑĤой
    -0.08
    æ±¹
    -0.08
    imar
    -0.08
    odo
    -0.08
    广
    -0.08
     Hier
    -0.08
     foremost
    -0.08
    Past
    -0.07
     sideways
    -0.07
    POSITIVE LOGITS
    个ä½ĵ
    0.22
    individual
    0.19
     individual
    0.19
    Individual
    0.18
     Individual
    0.18
     individually
    0.17
    _individual
    0.15
    个åĪ«
    0.15
     individ
    0.14
    个人
    0.14
    Activations Density 0.078%

    No Known Activations