© 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. 31898
    Prev
    Next
    INDEX
    Explanations

    as such

    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
    olio
    -0.09
    èĬĻ
    -0.08
    æĢµ
    -0.08
    agar
    -0.08
    дав
    -0.08
    é²ľæ´»
    -0.08
    é²ľèĬ±
    -0.08
    졸
    -0.08
    éĩijå±±
    -0.08
    getPost
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.15
    è¿Ļæł·åģļ
    0.12
    为æѤ
    0.12
    è¿ĻçĤ¹
    0.11
    éĤ£æł·çļĦ
    0.11
    è¿Ļä¹Īåģļ
    0.11
     ê·¸ëŁ¬
    0.10
    åĬŀäºĭ
    0.10
     váºŃy
    0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    0.10
    Activations Density 0.063%

    No Known Activations