© 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. 38935
    Prev
    Next
    INDEX
    Explanations

    received or soon

    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
    讳
    -0.08
    æĪIJå°±
    -0.08
    æĸ°åĨłçĸ«æĥħ
    -0.08
    åĴĮå®ĮåĸĦ
    -0.08
    å¸ĮæľĽèĩªå·±
    -0.08
    å®ĮæĪIJ
    -0.08
    沤
    -0.07
    ê°Ŀ
    -0.07
    æ±²
    -0.07
    åħ´èµ·
    -0.07
    POSITIVE LOGITS
    è¿Ļä¸ĢåĪ»
    0.12
    è¯ģåĪ¸æĬķèµĦ
    0.09
    驳
    0.09
    lhs
    0.09
    社ä¼ļåĮĸ
    0.09
    æĶĺ
    0.09
    accur
    0.09
    è´¨æĦŁ
    0.09
    ulty
    0.09
    AppComponent
    0.09
    Activations Density 0.005%

    No Known Activations