© 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. 36924
    Prev
    Next
    INDEX
    Explanations

    game style or aesthetic

    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
    ãĥįãĤ¿
    -0.11
    lef
    -0.09
     vad
    -0.09
    åħ¥ãĤĮ
    -0.09
    æ¥ł
    -0.09
    asser
    -0.09
    éĵ¶è¡Įä¸ļ
    -0.08
    çĻ½æ²Ļ
    -0.08
    çĤķ
    -0.08
    è¸Ŀ
    -0.08
    POSITIVE LOGITS
    é£İæł¼
    0.11
    åį¡éĢļ
    0.10
    èī²è°ĥ
    0.10
    èĬĴ
    0.09
    ç³ĸ
    0.09
    SEM
    0.09
    åįģéĩĮ
    0.09
    åŀ¢
    0.09
    å¤¸å¼ł
    0.08
    åĽ¤
    0.08
    Activations Density 0.203%

    No Known Activations