© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3301
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
    Negative Logits
    éĥ½å°Ĩ
    -0.26
    索尼
    -0.24
    -equiv
    -0.22
    èĢ¨
    -0.22
     sheets
    -0.21
    structured
    -0.21
    ollo
    -0.21
    earer
    -0.21
    ç½¢äºĨ
    -0.20
     sheet
    -0.20
    POSITIVE LOGITS
    phone
    0.26
    è¹²
    0.24
     phone
    0.23
     beep
    0.23
    æįİ
    0.23
     Phone
    0.22
    issy
    0.22
    åij¼
    0.22
    çĶµè¯Ŀ
    0.21
    lyn
    0.21
    Activations Density 0.009%

    No Known Activations