© 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. 5898
    Prev
    Next
    INDEX
    Explanations

    spent nuclear fuel

    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
    泡沫
    -0.10
    xBD
    -0.09
    æĬĺåıł
    -0.09
    æ´ŀ
    -0.09
    owski
    -0.09
    缸éĤ»
    -0.08
    esen
    -0.08
     HOUR
    -0.08
    äºķ
    -0.08
    Äł
    -0.08
    POSITIVE LOGITS
    æįIJåĬ©
    0.10
    ä¸Ģç«Ļ
    0.10
    ç»Ĥ
    0.09
    使ä¹ĭ
    0.09
    agog
    0.09
    éĵ
    0.09
    èĥ§
    0.09
    çĩĥæĸĻ
    0.09
    å¬Ĺ
    0.08
    ROY
    0.08
    Activations Density 0.048%

    No Known Activations