© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9854
    Prev
    Next
    INDEX
    Explanations

    years of

    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
    åIJĽåŃIJ
    -0.10
    è¿Ļåıª
    -0.09
    _FUN
    -0.09
    elah
    -0.09
    uter
    -0.09
     лиÑĨ
    -0.08
    irim
    -0.08
    ading
    -0.08
    ä¸Ģç¢Ĺ
    -0.08
    orce
    -0.08
    POSITIVE LOGITS
    æĻĸ
    0.10
     ÄIJình
    0.09
    çļĦçľ¼åħī
    0.09
    ä»Ģä¹Īä¸ľè¥¿
    0.09
    åħ¨å®¶
    0.09
    èĪįå¾Ĺ
    0.09
    濯
    0.08
    ç»ĨåĮĸ
    0.08
    -old
    0.08
     coeff
    0.08
    Activations Density 0.028%

    No Known Activations