© 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. 38662
    Prev
    Next
    INDEX
    Explanations

    means for

    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
    常å§Ķ
    -0.10
    ting
    -0.09
    enate
    -0.08
    gram
    -0.08
    omas
    -0.08
    ä¸ĩ象
    -0.08
    ç½ijç«Ļåľ°åĽ¾
    -0.08
    ông
    -0.08
    ging
    -0.08
     verm
    -0.08
    POSITIVE LOGITS
    麽
    0.09
    ropol
    0.09
    åŃ½
    0.09
    hift
    0.09
    ulty
    0.09
    ÑģÑĤÑĢ
    0.09
    esto
    0.09
     özellikle
    0.08
     unofficial
    0.08
    åľ¨æł¡
    0.08
    Activations Density 0.021%

    No Known Activations