© 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. 36852
    Prev
    Next
    INDEX
    Explanations

    state of

    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
    ä¸Ģ个个
    -0.11
    ä¸Ģ種
    -0.09
    两类
    -0.09
    两èĢħ
    -0.08
    ä¸Ģ个éĹ®é¢ĺ
    -0.08
    ä¸Ģç§į
    -0.08
    лог
    -0.08
    orno
    -0.08
    æѤ类
    -0.08
    ฯ
    -0.08
    POSITIVE LOGITS
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.11
     of
    0.10
    ylon
    0.09
    æĹ
    0.09
    ording
    0.09
    家åĸ»
    0.09
    éŁŃèıľ
    0.09
     của
    0.09
    ä»İæĿ¥æ²¡
    0.09
    grand
    0.09
    Activations Density 0.190%

    No Known Activations