© 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. 6489
    Prev
    Next
    INDEX
    Explanations

    who's next / who will

    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
    ä¸įåħ¬å¹³
    -0.10
    à¸Ļาม
    -0.09
    hower
    -0.08
    geb
    -0.08
     вполне
    -0.08
    æ§
    -0.08
    buster
    -0.08
    :Object
    -0.08
    adem
    -0.08
    esz
    -0.08
    POSITIVE LOGITS
     else
    0.14
    /how
    0.12
    soever
    0.11
    else
    0.11
    ever
    0.10
    æĿ¥åģļ
    0.10
    essim
    0.10
    ç½´
    0.09
    eger
    0.09
    hatt
    0.09
    Activations Density 0.021%

    No Known Activations