© 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. 55689
    Prev
    Next
    INDEX
    Explanations

    on hand or on board

    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
    å°ĺ
    -0.10
    è¹Ĭ
    -0.09
    åľ¨æѤ
    -0.09
    åıįä¹ĭ
    -0.09
    级åĪ«çļĦ
    -0.09
    ä¸İæѤåIJĮæŶ
    -0.09
    omer
    -0.09
    éķ¿è¿ľ
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    è¨ĢãģĪãģ°
    -0.08
    POSITIVE LOGITS
    /off
    0.10
    /on
    0.10
    ee
    0.09
    èĢķ
    0.09
    çķ´
    0.09
    æģŃ
    0.09
    egin
    0.08
    رش
    0.08
    æīĢæľī
    0.08
    éĶ·
    0.08
    Activations Density 0.006%

    No Known Activations