© 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. 51670
    Prev
    Next
    INDEX
    Explanations

    Arabic and Persian place names

    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¤ıæĹ¥
    -0.10
    æīĵäºĨ
    -0.09
    ä¸Ńç§ĭ
    -0.09
    fan
    -0.08
    积累
    -0.08
    aired
    -0.08
    èĮĥ
    -0.08
    åıijçĹħ
    -0.08
    underscore
    -0.08
    èİ«æĸ¯
    -0.08
    POSITIVE LOGITS
    æķĻçłĶ
    0.10
    åijĢ
    0.10
    .writ
    0.09
    欢è¿İæĤ¨
    0.09
    .Void
    0.09
    .tech
    0.08
    درج
    0.08
    _DIRECTION
    0.08
    è§ħ
    0.08
    æĮł
    0.08
    Activations Density 0.037%

    No Known Activations