© 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. 18852
    Prev
    Next
    INDEX
    Explanations

    damn, heck, tad, darn, earth

    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
    尤为
    -0.09
    ãģĵãģĿ
    -0.08
    渣
    -0.08
    iet
    -0.08
    .sym
    -0.08
    并ä¸į代表
    -0.08
    SY
    -0.07
    èīºæľ¯å®¶
    -0.07
    çī¹æ®ĬçļĦ
    -0.07
    cai
    -0.07
    POSITIVE LOGITS
    UTO
    0.10
    [](
    0.10
    .RunWith
    0.10
    pository
    0.09
    edo
    0.09
    ads
    0.09
    ä¸ĸçķĮä¸Ģæµģ
    0.09
     bè
    0.09
    æµĴ
    0.09
    ingly
    0.09
    Activations Density 0.004%

    No Known Activations