© 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. 50903
    Prev
    Next
    INDEX
    Explanations

    real word issues

    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
    çĻ»
    -0.11
    pure
    -0.10
    åħ¨å¥Ĺ
    -0.09
    onden
    -0.09
    天çĦ¶
    -0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.09
    enson
    -0.09
    æľºæ¢°åĮĸ
    -0.08
    enerator
    -0.08
    æī°
    -0.08
    POSITIVE LOGITS
     progress
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.09
    .named
    0.09
    åĢĴæĺ¯
    0.09
    è¿Ľå±ķ
    0.09
     Named
    0.09
    _named
    0.08
    è¿ĽæŃ¥
    0.08
    æĥ³äºĨæĥ³
    0.08
    sted
    0.08
    Activations Density 0.019%

    No Known Activations