© 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. 26446
    Prev
    Next
    INDEX
    Explanations

    unicode

    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
    ewe
    -0.10
    é¾Ļ头
    -0.09
    çĨ¨
    -0.09
    åŁºåĩĨ
    -0.09
    è¡ĮåĬ¨è®¡åĪĴ
    -0.08
    urga
    -0.08
    è¡Įåĭķ
    -0.08
     manufacturer
    -0.08
    GINE
    -0.08
    /kernel
    -0.08
    POSITIVE LOGITS
     uv
    0.10
    Unicode
    0.10
    çŁ³åĮĸ
    0.09
    éħįéŁ³
    0.09
    æĸ¹è¨Ģ
    0.08
    .ua
    0.08
    çĶ¥
    0.08
    æĭĪ
    0.08
    HS
    0.08
    unicode
    0.08
    Activations Density 0.242%

    No Known Activations