© 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. 33501
    Prev
    Next
    INDEX
    Explanations

    price, cost, money, value

    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
    ä¸ĢæľŁ
    -0.10
    owa
    -0.09
    æīĴ
    -0.09
    è¶ħ
    -0.09
    ÑģоÑģÑĤоÑı
    -0.09
    баÑĢ
    -0.09
    بة
    -0.09
    ä¸Ģ次
    -0.09
    hea
    -0.09
    UFF
    -0.09
    POSITIVE LOGITS
    NC
    0.09
    笼
    0.09
    ecer
    0.09
    éĢģåĩº
    0.09
    åģļä»Ģä¹Ī
    0.09
    ä»·ä½į
    0.08
    IDEO
    0.08
    elper
    0.08
     NC
    0.08
    OfType
    0.08
    Activations Density 0.031%

    No Known Activations