© 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. 51175
    Prev
    Next
    INDEX
    Explanations

    overall system or scheme

    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
    Popular
    -0.09
    æģŃ
    -0.09
    vez
    -0.09
    åī½
    -0.08
    æĺ±
    -0.08
    .Inner
    -0.08
    æѧ
    -0.08
    æĺ¯ä¸ŃåĽ½
    -0.08
    igi
    -0.08
     DEFINE
    -0.08
    POSITIVE LOGITS
    大å±Ģ
    0.16
    æķ´ä½ĵ
    0.14
     balance
    0.11
    çļĦæķ´ä½ĵ
    0.11
     overall
    0.11
    overall
    0.11
    平衡
    0.10
    åħ¨å±Ģ
    0.10
    Overall
    0.10
    æĢ»ä½ĵ
    0.10
    Activations Density 0.037%

    No Known Activations