© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19680
    Prev
    Next
    INDEX
    Explanations

    individual and individuals

    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
     Bos
    -0.09
    çļĦè¯Ŀé¢ĺ
    -0.09
    åıĭ们
    -0.08
     Finch
    -0.08
    éģį
    -0.08
    bos
    -0.08
    åŁĻ
    -0.08
    éķŃ
    -0.08
    emies
    -0.08
    æŁı
    -0.07
    POSITIVE LOGITS
    åĴĮ个人
    0.25
    个ä½ĵ
    0.23
     individuals
    0.20
    个人
    0.20
     individual
    0.20
    åĢĭ人
    0.20
    individual
    0.19
     Individuals
    0.18
    Individual
    0.17
    _individual
    0.17
    Activations Density 0.057%

    No Known Activations