© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51437
    Prev
    Next
    INDEX
    Explanations

    video game publishers and names

    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
     Trail
    -0.10
    ISTA
    -0.10
    ä¼Łå¤§
    -0.09
    éĩĩ
    -0.09
    ä¾£
    -0.09
    .utcnow
    -0.08
    Trail
    -0.08
    ç»°
    -0.08
    åħ¨å¥Ĺ
    -0.08
    æĶ¯
    -0.08
    POSITIVE LOGITS
    صاص
    0.10
    splash
    0.09
    xon
    0.09
    scr
    0.09
    æ¾Ī
    0.08
    enza
    0.08
    adden
    0.08
     غزة
    0.08
    ç²®
    0.08
    umph
    0.08
    Activations Density 0.003%

    No Known Activations