© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14658
    Prev
    Next
    INDEX
    Explanations

    phone calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    导读
    -0.24
    å¾ĹåĪĨ
    -0.21
    好人
    -0.20
    æį¢ä¸ª
    -0.20
    秩
    -0.19
    åıįçľģ
    -0.19
    Hidden
    -0.18
     Licht
    -0.18
    è°ı
    -0.18
    éĻĪåĪĹ
    -0.18
    POSITIVE LOGITS
    çĶµè¯Ŀ
    0.45
    éĽ»è©±
    0.37
    éĢļè¯Ŀ
    0.37
    æİ¥åIJ¬
    0.37
     phone
    0.36
     telephone
    0.31
    çĥŃ线
    0.30
    (phone
    0.29
    æīĵçĶµè¯Ŀ
    0.29
     telefon
    0.29
    Activations Density 0.051%

    No Known Activations