© 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. 18155
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code elements

    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¸įè¿ľ
    -0.07
    ä¹Łå°±æĺ¯
    -0.07
    /ws
    -0.07
    ãģĿãģĹãģ¦
    -0.07
     далек
    -0.07
    ler
    -0.07
    ç§ĭ
    -0.07
    -On
    -0.06
    iew
    -0.06
    ä¸įè¿ĩ
    -0.06
    POSITIVE LOGITS
    以ä¸ĬçļĦ
    0.10
    åĹŁ
    0.10
    èĦį
    0.10
    æŃ£åĢ¼
    0.10
    åīįèĢħ
    0.09
    çļĦæĥħ
    0.09
    ĪæĿĥ
    0.09
    åIJİèĢħ
    0.09
    è®´
    0.09
    èĥį
    0.09
    Activations Density 0.294%

    No Known Activations