© 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. 8619
    Prev
    Next
    INDEX
    Explanations

    hope followed by modal verb

    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
    åĩłä¹İ
    -0.15
    å¹¾ä¹İ
    -0.13
    åĩłä¹İæīĢæľī
    -0.12
    likely
    -0.11
     likely
    -0.11
    åĩłä¹İæĺ¯
    -0.10
    åĩłä¹İ没æľī
    -0.10
     probably
    -0.10
    åīįä¸Ģ天
    -0.09
     almost
    -0.09
    POSITIVE LOGITS
    æĹ©æĹ¥
    0.13
    èĥ½æī¾åĪ°
    0.12
    èĥ½è®©
    0.12
    ä¹Łèĥ½
    0.12
    æľīæīĢ帮åĬ©
    0.12
    ä¸įèĩ³äºİ
    0.12
    ä¸įè¦ģ太
    0.11
    èĥ½æĬĬ
    0.11
    èĥ½çľĭåĩº
    0.11
    èĥ½æ»¡è¶³
    0.11
    Activations Density 0.105%

    No Known Activations