© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 1389
    Prev
    Next
    INDEX
    Explanations

    US states and universities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    åħ¨éķĩ
    -0.26
    ç¾İåĨĽ
    -0.23
    ä¹ĭåĬĽ
    -0.23
    __$
    -0.23
    æ¸Ķèι
    -0.22
    æľ¬åħ¬åı¸
    -0.22
    -archive
    -0.22
     наÑģел
    -0.22
    xdc
    -0.21
    åŀĭä¼ģä¸ļ
    -0.21
    POSITIVE LOGITS
    åĮ»åѦéĻ¢
    0.36
    大åѦ
    0.30
    å¸ĪèĮĥ大åѦ
    0.27
     University
    0.25
    University
    0.25
     universities
    0.24
    åįı
    0.24
     campus
    0.24
     university
    0.24
     alum
    0.23
    Activations Density 0.023%

    No Known Activations