© 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. 21595
    Prev
    Next
    INDEX
    Explanations

    luxury

    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
    éħ¬
    -0.10
    chen
    -0.08
    åĬ²
    -0.08
    useum
    -0.08
    èį¤
    -0.08
    ilog
    -0.08
     Æ¡n
    -0.08
    isure
    -0.08
    itive
    -0.08
     Fuji
    -0.08
    POSITIVE LOGITS
    urious
    0.12
    ë¡Ń
    0.11
    ury
    0.11
    uries
    0.10
    embourg
    0.10
    liner
    0.10
    奢ä¾Ī
    0.09
    毯
    0.09
    à¸ĩาà¸Ļ
    0.09
    ä½ľåĵģåĨħ容
    0.08
    Activations Density 0.007%

    No Known Activations