© 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. 11465
    Prev
    Next
    INDEX
    Explanations

    to form a package

    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
    enci
    -0.11
    åģľä¸ĭ
    -0.10
    åı©
    -0.10
    зов
    -0.09
    æĬĵæįķ
    -0.09
    .getBean
    -0.09
     Amph
    -0.09
    æĬ½åĩº
    -0.09
    å¡«
    -0.09
    /twitter
    -0.09
    POSITIVE LOGITS
    以便
    0.09
    ç¼ļ
    0.09
    è¡Į车
    0.09
    ä¸į符åIJĪ
    0.09
    æĭĴ
    0.08
    å°±èĥ½å¤Ł
    0.08
    ä¸įå±ŀäºİ
    0.08
    个å¤ļ
    0.08
    éĺ²çĽĹ
    0.08
    ining
    0.08
    Activations Density 0.035%

    No Known Activations