© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 276
    Prev
    Next
    INDEX
    Explanations

    bigger or larger than

    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
    æ²¹èħ»
    -0.23
    èİ«è¿ĩäºİ
    -0.22
    çµ²
    -0.22
    evin
    -0.21
    ä¸Ŀ
    -0.21
    Gil
    -0.20
    Sil
    -0.20
    zza
    -0.20
    anny
    -0.19
    åľ¨æĪijåĽ½
    -0.19
    POSITIVE LOGITS
    æĽ´å¤§çļĦ
    0.23
    teen
    0.23
     Fundamental
    0.21
    ry
    0.21
    edata
    0.21
    åIJĪä½ľ
    0.21
    ç¦ģ
    0.20
    tures
    0.20
    itious
    0.20
    纵
    0.20
    Activations Density 0.015%

    No Known Activations