© 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. 38101
    Prev
    Next
    INDEX
    Explanations

    more or less

    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
    宣æī¬
    -0.09
     Patterson
    -0.09
    è¶ħé¢Ŀ
    -0.09
    å®ĹæŨ
    -0.09
    SizeMode
    -0.08
    æĤ¬å´ĸ
    -0.08
    人å±ħçݯå¢ĥ
    -0.08
    绾
    -0.08
    è¶ĬæĿ¥
    -0.08
     جدا
    -0.08
    POSITIVE LOGITS
     пÑĢог
    0.10
    enary
    0.09
    bling
    0.09
    iless
    0.09
    HEAD
    0.09
    è´µ
    0.08
    ADER
    0.08
     pena
    0.08
    ä»İä¸Ń
    0.08
    .gradle
    0.08
    Activations Density 0.279%

    No Known Activations