© 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. 21678
    Prev
    Next
    INDEX
    Explanations

    countries and nationalities

    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¯Ĵ
    -0.11
    âĶı
    -0.10
    å»ºåĽ½
    -0.09
    ç¨Ķ
    -0.09
    å®ļåIJij
    -0.09
    edom
    -0.09
    åħľ
    -0.09
    ç«ĭå¿Ĺ
    -0.09
    _IDENTIFIER
    -0.09
    ORIZONTAL
    -0.09
    POSITIVE LOGITS
    rew
    0.09
     rew
    0.09
    collapse
    0.09
    ä»İæĿ¥æ²¡
    0.08
    asi
    0.08
     Rear
    0.08
    ä¿®
    0.08
    åIJĪä½ľåħ³ç³»
    0.08
    ä»°
    0.08
    ä¿®çIJĨ
    0.08
    Activations Density 0.127%

    No Known Activations