© 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. 10473
    Prev
    Next
    INDEX
    Explanations

    Node-RED, QuickFix/J, ServiceMix, StreamSets Inc., core0, ltrasonography, Boots Up

    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
    èŀį
    -0.11
    è¿Ļ款
    -0.09
    æĬł
    -0.09
    åįĹæŀģ
    -0.08
    æĥ¶
    -0.08
    è¿Ļéĥ¨
    -0.08
    è¿Ļæł·åģļ
    -0.08
    æī¾äºĨ
    -0.08
    rek
    -0.08
    æīįè¡Į
    -0.08
    POSITIVE LOGITS
    éĹ·
    0.08
    ponsored
    0.08
     subrange
    0.08
    èį¨
    0.08
     Anat
    0.08
    çī§
    0.08
    /trunk
    0.08
    èįĴ
    0.08
    éĵĽ
    0.08
    åĿŀ
    0.08
    Activations Density 0.157%

    No Known Activations