© 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. 20824
    Prev
    Next
    INDEX
    Explanations

    commonly referred to as / commonly known as

    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
    åIJ¸åıĸ
    -0.09
    éªĭ
    -0.09
    å¾Ĺä½ı
    -0.08
    æŃ£èĥ½éĩı
    -0.08
    æķ£
    -0.08
    综åIJĪæ²»çIJĨ
    -0.08
    ä¸Ģ对
    -0.08
    æ·¼
    -0.08
     Kro
    -0.08
    纵深
    -0.08
    POSITIVE LOGITS
    ç®Ģ称
    0.13
    ä¿Ĺ称
    0.12
    ç®Ģ
    0.10
    _NM
    0.10
    ç°¡
    0.10
     abbreviated
    0.09
    legate
    0.09
    /plain
    0.09
    iffe
    0.08
     ì¤
    0.08
    Activations Density 0.135%

    No Known Activations