© 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. 55426
    Prev
    Next
    INDEX
    Explanations

    ski bindings and country skiing

    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
    æ´¥
    -0.09
     co
    -0.09
    æŀĦæĪIJ
    -0.08
     mish
    -0.08
     elevator
    -0.08
     cab
    -0.08
    ä¼¢
    -0.08
    åѦåīį
    -0.08
     bott
    -0.08
    _tF
    -0.08
    POSITIVE LOGITS
    à¹ģรà¸ĩ
    0.10
    çī¹æľĹ
    0.09
    ç¥ī
    0.09
    ä¸Ŀè·¯
    0.09
    ç©´
    0.09
    äºĨä¸Ģåľº
    0.09
    滤
    0.09
    éļĶéŁ³
    0.09
    ÑģÑĤÑĢо
    0.09
    å¤ĸ交éĥ¨
    0.09
    Activations Density 0.213%

    No Known Activations