© 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. 3669
    Prev
    Next
    INDEX
    Explanations

    all that

    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
    èİ«æĸ¯
    -0.09
    PropertyName
    -0.09
    bish
    -0.09
    olta
    -0.09
    éģŃåıĹ
    -0.09
    è¿Ļä¸Ģ天
    -0.09
    èĦ¾æ°Ķ
    -0.09
    íĮIJ
    -0.09
    gers
    -0.09
    quette
    -0.08
    POSITIVE LOGITS
    åī©ä¸ĭ
    0.09
    åŁł
    0.08
    eso
    0.08
    uye
    0.08
    igner
    0.08
    fter
    0.08
    æľ¬æľŁ
    0.08
    flux
    0.08
    ien
    0.07
    é¢ĺ主
    0.07
    Activations Density 0.007%

    No Known Activations