© 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. 11186
    Prev
    Next
    INDEX
    Explanations

    amounts of money

    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
    eras
    -0.11
    åĿİ
    -0.09
    å¨ĺå¨ĺ
    -0.08
    éļĽ
    -0.08
    anden
    -0.08
    ÙĬتÙĩ
    -0.08
    æĺ¥ç§ĭ
    -0.08
    /end
    -0.08
    çİĩè¾¾åĪ°
    -0.08
    hill
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.13
    åºł
    0.11
    éĥ½è§īå¾Ĺ
    0.10
    æŀĭ
    0.10
    å¤ļåľ°
    0.09
    çŃł
    0.09
    onn
    0.09
    综åIJĪæķ´æ²»
    0.09
    çºĽ
    0.08
    åĸĦ
    0.08
    Activations Density 0.027%

    No Known Activations