© 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. 38311
    Prev
    Next
    INDEX
    Explanations

    multi-talented, versatile, all-rounder

    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
    çĽĽå¤§
    -0.09
    OPY
    -0.09
    ogr
    -0.09
    ä¸Ģ大
    -0.08
    /arch
    -0.08
    æ°¸ä¹ħ
    -0.08
    çŁŃ
    -0.08
     matching
    -0.08
    æĺ¯ä»¥
    -0.08
    DIRECT
    -0.08
    POSITIVE LOGITS
    åħ¨èĥ½
    0.21
     versatility
    0.17
     versatile
    0.16
    å¤ļåĬŁèĥ½
    0.14
    åħ¼
    0.14
    åħ¨éĿ¢åıijå±ķ
    0.14
    èĥ½åĬĽå¼º
    0.14
    å¤ļç§į
    0.13
    å¤ļæł·
    0.12
    综åIJĪæĢ§
    0.12
    Activations Density 0.152%

    No Known Activations