© 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. 62379
    Prev
    Next
    INDEX
    Explanations

    Copyright and licenses

    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
    ç¥Ģ
    -0.11
    æķĻä¼ļ
    -0.09
    auga
    -0.09
    å¥ĩ
    -0.08
    æĬµæĬĹ
    -0.08
    对æĬĹ
    -0.08
    禺
    -0.08
    ç¥Ń
    -0.08
    æıı
    -0.08
    ÊĴ
    -0.08
    POSITIVE LOGITS
    ä½Ľæ³ķ
    0.13
    æĤŃ
    0.13
    èı©æıIJ
    0.12
    ä¾Ľåħ»
    0.12
     Budd
    0.11
    ç¥ŀéĢļ
    0.11
    ä½ĽæķĻ
    0.11
    å¼ŁåŃIJ
    0.11
    ä¿®è¡Į
    0.11
     Buddhist
    0.11
    Activations Density 0.092%

    No Known Activations