© 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. 56004
    Prev
    Next
    INDEX
    Explanations

    space, moon, and orbit

    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¸įæĸŃçļĦ
    -0.08
    å¤ļãģĦ
    -0.08
    æĸ°åĵģ
    -0.08
    ìĽĥ
    -0.08
    ickle
    -0.08
     humble
    -0.08
    PEC
    -0.08
    çķĻè¨ĢæĿ¿
    -0.08
    ovich
    -0.08
    å¹³éĿĻ
    -0.08
    POSITIVE LOGITS
    å°ıå¾®ä¼ģä¸ļ
    0.09
    .tie
    0.09
    åĿIJ
    0.09
    ris
    0.09
    åĨ²åĪº
    0.09
    触åıĬ
    0.08
    èī°
    0.08
    å¾ģæĪĺ
    0.08
    /tab
    0.08
    å®ŀä½ĵ
    0.08
    Activations Density 0.035%

    No Known Activations