© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21109
    Prev
    Next
    INDEX
    Explanations

    St. [name]'s institution

    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
    åªĽ
    -0.10
    ousse
    -0.09
    çļĦåĪ©çĽĬ
    -0.09
    ä¸Ģæīĭ
    -0.09
    çīĩåĮº
    -0.09
    èĶ»
    -0.09
    _SENSOR
    -0.09
    _zones
    -0.09
    åħ¥é©»
    -0.09
     Ðijа
    -0.08
    POSITIVE LOGITS
    人士
    0.08
    hoc
    0.08
    é«ĺä¸ŃçĶŁ
    0.08
    幡
    0.08
     æŀ
    0.08
    è¾ĵç»Ļ
    0.08
    ç¡ĸ
    0.08
    åıĸ代
    0.08
    feito
    0.08
     spar
    0.08
    Activations Density 0.017%

    No Known Activations