© 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. 57855
    Prev
    Next
    INDEX
    Explanations

    Apple device and model names

    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
    害
    -0.09
    ä¸ĸ家
    -0.09
    åĺ»åĺ»
    -0.08
    STOP
    -0.08
    solete
    -0.08
    Advisor
    -0.08
    æĮ¯åħ´
    -0.08
    å©Ģ
    -0.08
    æݪæĸ½
    -0.08
    åIJ¸å¼ķ
    -0.08
    POSITIVE LOGITS
    tons
    0.09
    iliar
    0.09
    å±ı
    0.09
    ãģĦãģĭ
    0.08
     Brig
    0.08
    IAL
    0.08
    ä»Ļå¢ĥ
    0.08
    蹶
    0.08
    gni
    0.08
    ós
    0.08
    Activations Density 0.017%

    No Known Activations