© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35374
    Prev
    Next
    INDEX
    Explanations

    future, possibility, or extent

    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
    dee
    -0.08
    说æĺİ
    -0.08
    stroke
    -0.08
    eric
    -0.08
    ter
    -0.08
    é«»
    -0.08
     Sao
    -0.08
    ayan
    -0.08
    éħ¬
    -0.08
    为é¦ĸçļĦ
    -0.08
    POSITIVE LOGITS
    emente
    0.11
    ably
    0.11
    (expect
    0.10
    ä¹İ
    0.10
    zelf
    0.09
    LY
    0.09
    èĢ³è¾¹
    0.09
    ython
    0.09
    ackson
    0.09
    elson
    0.09
    Activations Density 0.002%

    No Known Activations