© 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. 37209
    Prev
    Next
    INDEX
    Explanations

    on the other hand

    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
    çĩİ
    -0.10
    äºĨä¸ĢäºĽ
    -0.10
    ä¸Ģéĺµ
    -0.10
    äºĨä¸Ģæī¹
    -0.09
     eup
    -0.09
    ä¸Ģ大æī¹
    -0.09
    æ°§åĮĸ
    -0.09
    è³ĵ
    -0.09
    便ä¼ļ
    -0.09
    èĢĮä¸Ķè¿ĺ
    -0.09
    POSITIVE LOGITS
     meanwhile
    0.17
    åĪĻæĺ¯
    0.16
    åĪĻ
    0.14
    Meanwhile
    0.12
    åı¦ä¸Ģæĸ¹éĿ¢
    0.12
    åīĩ
    0.11
     Meanwhile
    0.11
    ï¼ĮåĪĻ
    0.10
     же
    0.10
    antz
    0.09
    Activations Density 0.027%

    No Known Activations