© 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. 2928
    Prev
    Next
    INDEX
    Explanations

    raising funds for charity

    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
    çŃīçĿĢ
    -0.10
    é¦Ī
    -0.10
    /out
    -0.09
    塬
    -0.09
    ody
    -0.09
    ODY
    -0.09
    ë¡ł
    -0.08
    esy
    -0.08
    .echo
    -0.08
    pery
    -0.08
    POSITIVE LOGITS
    æĻ®
    0.10
    åѤåĦ¿
    0.08
    åı¸
    0.08
    太æ¹ĸ
    0.08
     trends
    0.08
    åĪ»èĭ¦
    0.08
    YM
    0.08
    oris
    0.08
    han
    0.07
    hub
    0.07
    Activations Density 0.010%

    No Known Activations