© 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. 51141
    Prev
    Next
    INDEX
    Explanations

    deep threat, visual information, close-up, myopia

    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
    å¾ĹåĪĨ
    -0.09
    åĸĻ
    -0.08
     Heating
    -0.08
    楯
    -0.08
    åħ¨èĥ½
    -0.08
     поÑĢÑĤал
    -0.08
    ustain
    -0.08
    æ¯ķç«Ł
    -0.08
    Ñģи
    -0.08
    çıĬ
    -0.08
    POSITIVE LOGITS
    _DISPATCH
    0.09
    rap
    0.09
    elong
    0.09
    å¤Ħç½®
    0.09
    cek
    0.09
    ypi
    0.09
    åĩĿ
    0.08
     Dispatch
    0.08
     dispatched
    0.08
    é«ĺçŃī
    0.08
    Activations Density 0.064%

    No Known Activations