© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19868
    Prev
    Next
    INDEX
    Explanations

    player and media playback

    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
    abad
    -0.09
    elligent
    -0.08
    ammers
    -0.08
    æĶ¶éĽĨ
    -0.08
    lte
    -0.08
    漩
    -0.08
    ç«ĭå¿Ĺ
    -0.08
    æ±
    -0.08
    å·§
    -0.08
    à¸ķà¸ģ
    -0.08
    POSITIVE LOGITS
    æĴŃæĶ¾
    0.18
     playback
    0.10
    æĴŃ
    0.10
     radio
    0.09
     MediaPlayer
    0.09
    å¡ĺ
    0.09
    Radio
    0.09
    .listen
    0.09
     Playback
    0.09
    éŁ³é¢ij
    0.09
    Activations Density 0.109%

    No Known Activations