© 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. 32410
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    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
    ohn
    -0.09
    ä¸Ń央
    -0.09
    _prim
    -0.09
     ÑģÑĤанов
    -0.09
    èªĵè¨Ģ
    -0.09
    lops
    -0.08
    entifier
    -0.08
    azed
    -0.08
    姬
    -0.08
    å¾ĹäºĨ
    -0.08
    POSITIVE LOGITS
    ä¸Ģä½ĵ
    0.09
    èįĥ
    0.09
    èĹī
    0.09
    æĦı大
    0.09
    éĶ¦æłĩ
    0.08
    æĨĶ
    0.08
    ä¸Ģå¤ľ
    0.08
    æľīçļĦ人
    0.08
    åĪĨéĴŁåIJİ
    0.08
    æ¥
    0.08
    Activations Density 0.026%

    No Known Activations