© 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. 21217
    Prev
    Next
    INDEX
    Explanations

    for

    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
    ãģĬ
    -0.23
    人éĥ½
    -0.18
    ãģĻãģIJãģ«
    -0.15
    ãģĤãĤĭ
    -0.15
    æŶåĢĻ
    -0.15
    ãģĬ話
    -0.15
    ãģĤ
    -0.13
    ãģĤãģ£ãģ¦
    -0.13
    对äºİ
    -0.13
    ãģĤãĤĭç¨ĭ度
    -0.13
    POSITIVE LOGITS
    bidden
    0.24
    -profit
    0.18
    geries
    0.18
     purposes
    0.15
    /from
    0.15
     reasons
    0.14
    ges
    0.14
    /of
    0.14
    king
    0.13
    _each
    0.13
    Activations Density 0.717%

    No Known Activations