© 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. 8900
    Prev
    Next
    INDEX
    Explanations

    action completed or state set

    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
    ç»ıåİĨäºĨ
    -0.09
     SEE
    -0.09
    ç´§è·Ł
    -0.08
    ึà¸ģ
    -0.08
     requestId
    -0.08
    ä¸ĵæłı
    -0.08
    让大家
    -0.08
     доп
    -0.08
    0
    -0.08
    åģ¥
    -0.08
    POSITIVE LOGITS
    æijĩ
    0.10
    å±ķåĩº
    0.09
    åĩºæĿ¥
    0.09
    åĬłæĮģ
    0.09
    ì±Ħ
    0.09
    éĿ¢åĮħ
    0.09
    ROAD
    0.09
    å¯Ĵ
    0.08
    ÐĵÐŀ
    0.08
    åĽ«
    0.08
    Activations Density 0.177%

    No Known Activations