© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7622
    Prev
    Next
    INDEX
    Explanations

    court claims and office names

    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
     Intelli
    -0.08
    atch
    -0.08
    丧失
    -0.08
    .listFiles
    -0.08
     upside
    -0.08
    iras
    -0.08
    诰
    -0.08
    cul
    -0.08
     Ze
    -0.08
     Hick
    -0.07
    POSITIVE LOGITS
    æIJ½
    0.10
    åŃij
    0.10
    ç»Į
    0.09
    çݰ代åĨľä¸ļ
    0.09
    æİIJ
    0.09
    éĻĮçĶŁ
    0.09
    估计
    0.09
    æŁ¬
    0.08
    åħĶ
    0.08
    æĭ±
    0.08
    Activations Density 0.003%

    No Known Activations