© 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. 3592
    Prev
    Next
    INDEX
    Explanations

    wide receiver

    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
     Archer
    -0.09
    æĬ½åĩº
    -0.09
    å´½
    -0.08
    éļĶéŁ³
    -0.08
    .toBe
    -0.08
    eny
    -0.08
    æĭ¦æĪª
    -0.08
     nord
    -0.08
    åĴķ
    -0.08
    ä»ĬçĶŁ
    -0.08
    POSITIVE LOGITS
    çī§
    0.09
    rice
    0.09
    èłķ
    0.09
    大æĪ·
    0.08
    滥
    0.08
    åĢ¾
    0.08
    ullah
    0.08
    ouri
    0.08
    ä½łçľĭ
    0.08
    å¾Īæĸ¹ä¾¿
    0.08
    Activations Density 0.207%

    No Known Activations