© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51399
    Prev
    Next
    INDEX
    Explanations

    drinks, food, and natural products

    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
    èĮ«èĮ«
    -0.11
    å¿Ļ
    -0.11
    eries
    -0.09
     sidel
    -0.08
    _COMPAT
    -0.08
    kw
    -0.08
    suming
    -0.08
    åľ°ä¸Ńæµ·
    -0.08
    å±Ģéĥ¨
    -0.08
     Junction
    -0.08
    POSITIVE LOGITS
    é³ı
    0.10
    éľ°
    0.09
    è°
    0.09
    åIJĪ
    0.09
    移åĪ°
    0.08
    urity
    0.08
    èijĽ
    0.08
    격
    0.08
    轿
    0.08
    è²¼
    0.08
    Activations Density 0.067%

    No Known Activations