© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 22927
    Prev
    Next
    INDEX
    Explanations

    future events or possibilities

    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
    ç¾½æ¯Ľ
    -0.10
    åı¯ä»¥èİ·å¾Ĺ
    -0.10
    ä»ĬæĻļ
    -0.09
    å°ıæĹ¶åīį
    -0.09
    è¿Ļæīį
    -0.09
    .Abs
    -0.09
    ä¼ļä¸įä¼ļ
    -0.09
    æĪIJè´¥
    -0.08
    è¾Ľ
    -0.08
    ฯ
    -0.08
    POSITIVE LOGITS
    rip
    0.09
    omal
    0.08
    åijĪçݰåĩº
    0.08
    ial
    0.08
    ricular
    0.08
    AMESPACE
    0.08
     fing
    0.08
    èµ·åΰ
    0.08
    ä¸ĩäºĭ
    0.08
    ebra
    0.08
    Activations Density 0.105%

    No Known Activations