© 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. 30725
    Prev
    Next
    INDEX
    Explanations

    not a single

    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
    羣çļĦå¾Ī
    -0.09
    å¾Īæĥ³
    -0.09
    ä¸ĢäºĽ
    -0.09
    hin
    -0.09
    ä¸ĢåĪĩéĥ½
    -0.08
    羣çļĦæĺ¯
    -0.08
    _US
    -0.08
    éľ°
    -0.08
    rome
    -0.08
    å¾Īéĩįè¦ģ
    -0.08
    POSITIVE LOGITS
    æİĴåIJį第
    0.10
    icot
    0.09
    éĵ²
    0.09
    åĽºå®ļçļĦ
    0.09
    容纳
    0.09
    iterr
    0.09
    ç»Ī身
    0.09
    æĮijåīĶ
    0.09
    æĪĸå¤ļ
    0.08
    leness
    0.08
    Activations Density 0.030%

    No Known Activations