© 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. 51012
    Prev
    Next
    INDEX
    Explanations

    PGA Tour, ATP Tour, Challenger

    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
    gebung
    -0.10
    ening
    -0.10
    edata
    -0.09
    аÑĤÑĥÑĢ
    -0.08
    cust
    -0.08
    ç¼ļ
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    ened
    -0.08
    å¡ijèĥ¶
    -0.08
    creasing
    -0.08
    POSITIVE LOGITS
     manh
    0.09
    tran
    0.09
    licensed
    0.08
    èįĴ
    0.08
    urm
    0.08
    èIJ½åħ¥
    0.08
    æ©Ľ
    0.08
     Anth
    0.08
    /or
    0.08
    addy
    0.08
    Activations Density 0.003%

    No Known Activations