© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56039
    Prev
    Next
    INDEX
    Explanations

    relentless, ruthless, or incessant actions

    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
    andom
    -0.09
    å¾Ĺèµ·
    -0.08
     thai
    -0.08
    ä¸įä¸ĭ
    -0.08
    æĶ¿çŃĸæݪæĸ½
    -0.08
    ä¸Ģåij³
    -0.08
    æį¢åı¥è¯Ŀ说
    -0.08
    (tf
    -0.08
    неÑĨ
    -0.08
    ularity
    -0.07
    POSITIVE LOGITS
    ently
    0.11
    追éĹ®
    0.10
    æĹłæĥħ
    0.09
     pace
    0.09
     Pace
    0.09
    ç¶ļ
    0.09
    èģĴ
    0.09
    ç¶ļãģı
    0.09
    强åĬ²
    0.09
    æıIJéĹ®
    0.08
    Activations Density 0.007%

    No Known Activations