© 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. 9016
    Prev
    Next
    INDEX
    Explanations

    rent / renting

    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
    oute
    -0.10
    ulent
    -0.10
    罡
    -0.09
     tÆ°
    -0.08
    Prince
    -0.08
    hood
    -0.08
    æ§Ĭ
    -0.08
    neath
    -0.08
     Gór
    -0.08
    Nested
    -0.08
    POSITIVE LOGITS
     apocalypse
    0.10
    æģģ
    0.09
    个æĢ§
    0.09
     Hick
    0.08
    é¦
    0.08
    aptured
    0.08
    ialized
    0.08
    ÑĤеÑĢ
    0.08
    ÙģاÙĤ
    0.08
    IALIZ
    0.08
    Activations Density 0.011%

    No Known Activations