© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30595
    Prev
    Next
    INDEX
    Explanations

    incoming mail or messages

    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
    é²ł
    -0.10
    åıij声
    -0.09
    åī¥å¤º
    -0.09
    éĢģä¸Ĭ
    -0.09
    ç»ijæŀ¶
    -0.09
    宣讲
    -0.09
    SHARE
    -0.08
    究
    -0.08
    illin
    -0.08
    广æĴŃ
    -0.08
    POSITIVE LOGITS
    æīij
    0.10
    (IM
    0.10
    PILE
    0.09
    åį§
    0.09
     incoming
    0.09
     Incoming
    0.09
    Incoming
    0.09
    害
    0.09
    æ±²
    0.09
     IM
    0.09
    Activations Density 0.112%

    No Known Activations