© 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. 49089
    Prev
    Next
    INDEX
    Explanations

    cust/custard/customer

    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
    eyer
    -0.10
    ickey
    -0.10
    èĩªçĦ¶ä¿ĿæĬ¤
    -0.10
    enie
    -0.10
     jeżeli
    -0.09
    ennes
    -0.09
    é£Ĵ
    -0.09
    å°ī
    -0.09
    ä¼ļä¸Ĭ
    -0.09
    sburg
    -0.08
    POSITIVE LOGITS
    mia
    0.10
    loe
    0.09
    backward
    0.09
     blind
    0.09
    GLOBALS
    0.09
    ä¸įåĩº
    0.09
    ral
    0.08
     полов
    0.08
    cle
    0.08
    obl
    0.08
    Activations Density 0.003%

    No Known Activations