© 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. 183
    Prev
    Next
    INDEX
    Explanations

    telephone infrastructure and services

    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
    é²²
    -0.28
    丰ç¡ķ
    -0.23
    algo
    -0.23
    鬥
    -0.22
    LAG
    -0.22
    isable
    -0.22
    éĢłèĪ¹
    -0.21
    èĨĺ
    -0.21
    PACK
    -0.21
    æ²¹èĦĤ
    -0.21
    POSITIVE LOGITS
    çĶµè¯Ŀ
    0.40
     telephone
    0.37
     phone
    0.37
    åı·çłģ
    0.34
    éĽ»è©±
    0.34
    phone
    0.34
    æĭ¨æīĵ
    0.33
     Telephone
    0.33
    -phone
    0.32
    _phone
    0.32
    Activations Density 0.018%

    No Known Activations