© 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. 18734
    Prev
    Next
    INDEX
    Explanations

    on [material|surface|timing]

    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
    åĭ¤
    -0.09
    rief
    -0.08
    ãĤ
    -0.08
    è¿Ļæł·åģļ
    -0.08
     пеÑĢи
    -0.08
    .Components
    -0.08
    kit
    -0.08
     traffic
    -0.08
    eldom
    -0.08
    åľºä¸Ĭ
    -0.08
    POSITIVE LOGITS
    æ·±åİļçļĦ
    0.13
    åīįçŀ»æĢ§
    0.10
    Mahon
    0.09
    åģı
    0.09
    ä¸ĢæµģçļĦ
    0.09
    æĬ¢
    0.09
    æ·±åİļ
    0.09
    åħ¨æĹ¥
    0.09
     hint
    0.09
    hint
    0.09
    Activations Density 0.050%

    No Known Activations