© 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. 20477
    Prev
    Next
    INDEX
    Explanations

    order: first, then

    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
    åĬ©
    -0.10
    娱
    -0.09
    è¿ĺä¸įå¤Ł
    -0.09
    廪
    -0.09
    oldt
    -0.08
    åĬ³åĬ¨
    -0.08
    artial
    -0.08
     Sole
    -0.08
    对æīĭ
    -0.08
    _corpus
    -0.08
    POSITIVE LOGITS
    åħĪ
    0.23
    åħĪè¡Į
    0.21
    åħĪæĬĬ
    0.16
    æľĢåħĪ
    0.16
    åħĪæĺ¯
    0.15
     먼ìłĢ
    0.15
    åħĪ导
    0.15
    ä¼ĺåħĪ
    0.15
     precedence
    0.12
    먼
    0.12
    Activations Density 0.144%

    No Known Activations