© 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. 30672
    Prev
    Next
    INDEX
    Explanations

    asking why

    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
    locale
    -0.08
    éĢģåĩº
    -0.08
    è°Ĩ
    -0.08
    AppBundle
    -0.08
    sex
    -0.08
    æ°¸è¿ľä¸įä¼ļ
    -0.08
    åķĨä¼ļ
    -0.08
    åĨ®
    -0.07
    -tier
    -0.07
     disclaimer
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹ĪåİŁåĽł
    0.10
    amt
    0.10
     reasons
    0.10
    ammo
    0.10
    eer
    0.10
    åĬ¬
    0.10
    DL
    0.10
    为ä»Ģä¹Īè¦ģ
    0.09
    建åĨĽ
    0.09
     cán
    0.09
    Activations Density 0.071%

    No Known Activations