© 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. 29765
    Prev
    Next
    INDEX
    Explanations

    title and tuition fee

    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
    滩
    -0.09
    tober
    -0.09
    ness
    -0.09
    alth
    -0.09
     СовеÑĤ
    -0.08
    inh
    -0.08
     reluct
    -0.08
    -0.08
     biá»ĩt
    -0.08
    çªĿ
    -0.08
    POSITIVE LOGITS
    amu
    0.13
    mate
    0.10
    itional
    0.10
    è¿·èĮ«
    0.09
    NING
    0.09
    rog
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    èĩ¾
    0.09
    é«ĺæĺĤ
    0.09
    åİ¿åħ¬å®īå±Ģ
    0.09
    Activations Density 0.001%

    No Known Activations