© 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. 20159
    Prev
    Next
    INDEX
    Explanations

    torrent and peer-related terms

    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
     ÑģовеÑĤ
    -0.10
    ritel
    -0.09
    Spo
    -0.09
     Spo
    -0.09
    ewriter
    -0.09
    .compose
    -0.09
    è¿ģ
    -0.08
    éĵ¿
    -0.08
    _PW
    -0.08
    Bush
    -0.08
    POSITIVE LOGITS
    Torrent
    0.12
     torrent
    0.11
     peer
    0.11
     Torrent
    0.10
     Peer
    0.10
    ä¸ĢåĪĨ
    0.10
     peers
    0.10
     torrents
    0.10
    èݲèĬ±
    0.09
     Lair
    0.09
    Activations Density 0.071%

    No Known Activations