© 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. 3007
    Prev
    Next
    INDEX
    Explanations

    bank accounts and banking services

    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
    .getAs
    -0.09
    æļ§
    -0.09
    vin
    -0.09
    erÃŃa
    -0.08
    å³°
    -0.08
    æīĭæĦŁ
    -0.08
    ithe
    -0.08
    ocoder
    -0.08
    é¹Ĭ
    -0.08
     rozwiÄħz
    -0.08
    POSITIVE LOGITS
    åĢļ
    0.10
    odal
    0.09
    æĹ©å°±
    0.09
    åijĬ
    0.09
    马æĭī
    0.09
    å²Ļ
    0.09
    对åѦçĶŁ
    0.09
    è¯ı
    0.09
    night
    0.08
    isan
    0.08
    Activations Density 0.011%

    No Known Activations