© 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. 53317
    Prev
    Next
    INDEX
    Explanations

    flash camera

    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
    综åIJĪæĢ§
    -0.09
    æĨ¨
    -0.09
    ENE
    -0.09
    å®ļä½į
    -0.08
    æĺİæĺ¾çļĦ
    -0.08
    ÑģоÑģ
    -0.08
     outnumber
    -0.08
    è§Ĩ为
    -0.08
    è¦ĸ
    -0.08
    Scalars
    -0.08
    POSITIVE LOGITS
    евиÑĩ
    0.09
    çģ«å±±
    0.09
    undred
    0.09
    对ä»ĺ
    0.08
    éħį
    0.08
    useum
    0.08
    /GPL
    0.08
    å°ijéĩı
    0.08
    éªĺ
    0.08
    ฯ
    0.08
    Activations Density 0.008%

    No Known Activations