© 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. 50425
    Prev
    Next
    INDEX
    Explanations

    space fiction and stars

    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
    å¶
    -0.10
    å¤ĸ交éĥ¨
    -0.09
    ç¯ģ
    -0.09
    âľķ
    -0.08
    orary
    -0.08
    èĩº
    -0.08
     Covenant
    -0.08
    ç»¿åľ°
    -0.08
    è¾ĩ
    -0.08
    sWith
    -0.08
    POSITIVE LOGITS
    ç«ĭ项
    0.09
    ç»´
    0.09
     Pig
    0.09
    èĭ±çī¹
    0.09
    ç¶Ń
    0.08
    ucken
    0.08
     اÙĦØ£ÙĪ
    0.08
    å±İ
    0.08
    社ä¼ļåıijå±ķ
    0.08
    ç³Ł
    0.08
    Activations Density 0.080%

    No Known Activations