© 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. 35533
    Prev
    Next
    INDEX
    Explanations

    customer service and support

    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
    缦
    -0.10
    让æ¶Īè´¹èĢħ
    -0.10
     Redistributions
    -0.09
    AZE
    -0.09
    chron
    -0.09
    bsp
    -0.09
    CCR
    -0.09
    åģļåĪ°äºĨ
    -0.09
    使çĶ¨æĿĥ
    -0.09
    _callbacks
    -0.09
    POSITIVE LOGITS
    ArrayType
    0.11
    导åIJij
    0.09
    æ¸İ
    0.09
    ä¼¢
    0.08
    çŁ¥éģĵèĩªå·±
    0.08
    沤
    0.08
    çĹĶ
    0.08
    à¹Į
    0.08
    俱ä¹IJ
    0.08
    æĢ¿
    0.07
    Activations Density 0.021%

    No Known Activations