© 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. 39119
    Prev
    Next
    INDEX
    Explanations

    let

    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
    马åĬĽ
    -0.10
    åģ¥åº·çļĦ
    -0.09
    è¯ķéªĮ
    -0.09
     rushes
    -0.09
    çīĮ
    -0.08
    æ°ijæĶ¿å±Ģ
    -0.08
    俾
    -0.08
    åIJįçīĮ
    -0.08
    éĥĦ
    -0.08
    9
    -0.08
    POSITIVE LOGITS
    ç¦ģ
    0.09
    à¹Ģà¸Ħร
    0.09
    CKER
    0.09
    FILES
    0.09
    ç¨Ģ
    0.08
     ÙĪاÙĦØŃ
    0.08
    ái
    0.08
    éļıå¤Ħ
    0.08
    åĨĴ
    0.08
    å¸Į
    0.08
    Activations Density 0.003%

    No Known Activations