© 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. 7878
    Prev
    Next
    INDEX
    Explanations

    Salvation, Destiny, saved, people

    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
    ç¾¤å²Ľ
    -0.09
    brid
    -0.09
    åĵĦ
    -0.09
    åĵ¼
    -0.09
    гла
    -0.08
    æ¬ł
    -0.08
    åIJ¯åıij
    -0.08
    _gener
    -0.08
    èĩ¾
    -0.08
    Pad
    -0.08
    POSITIVE LOGITS
    .isSelected
    0.11
    å·¥ä½ľç»Ħ
    0.10
    使åij½
    0.10
    ä¸ĢæĹı
    0.10
    éĢī
    0.10
    ä¸İä¼Ĺä¸įåIJĮ
    0.09
    èĩªè´¸åĮº
    0.09
    ecc
    0.09
    æ¶Ī
    0.09
    å¥ij约
    0.09
    Activations Density 0.034%

    No Known Activations