© 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. 55496
    Prev
    Next
    INDEX
    Explanations

    Brighton, polo, Aman, Tritone

    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
    ä»Ħ
    -0.10
    ussy
    -0.09
    éºŁ
    -0.09
    ingly
    -0.08
    itty
    -0.08
     Mặt
    -0.08
    åIJĮåŁİ
    -0.08
    INGTON
    -0.08
    ìľ¨
    -0.08
    cept
    -0.08
    POSITIVE LOGITS
    ê¶Į
    0.10
    å½ĵä¹ĭæĹłæĦ§
    0.09
    渺
    0.09
    èĹ»
    0.09
    _VIRTUAL
    0.08
    ä¹ĭ乡
    0.08
    泡沫
    0.08
    çĸĹ
    0.08
    æīĢæıIJä¾Ľ
    0.08
    èIJ¥æĶ¶
    0.08
    Activations Density 0.004%

    No Known Activations