© 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. 6930
    Prev
    Next
    INDEX
    Explanations

    solitary, shy, withdrawn, reclusive

    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
    å¹³æķ´
    -0.09
    失
    -0.09
    åĮħ袱
    -0.08
    _locked
    -0.08
    itating
    -0.08
    å°Ĩäºİ
    -0.08
    ibur
    -0.08
    &gt
    -0.08
    èĥ½ä½¿
    -0.08
     Tail
    -0.08
    POSITIVE LOGITS
    éĿ¢åħ·
    0.10
    åѤçĭ¬
    0.10
    beck
    0.09
     Fet
    0.09
    è¯Ŀ说
    0.09
    é»
    0.08
    unker
    0.08
     vard
    0.08
     Withdraw
    0.08
    主åĬ¨
    0.08
    Activations Density 0.013%

    No Known Activations