© 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. 14687
    Prev
    Next
    INDEX
    Explanations

    reporting speech or writing

    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
    ç²ī
    -0.21
    è´²
    -0.20
    erer
    -0.19
    å²Į
    -0.19
    é¢ĨåŁŁ
    -0.18
     tops
    -0.18
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.18
    çĶŁç´ł
    -0.18
    æĻĭ级
    -0.17
    示èĮĥåŁºåľ°
    -0.17
    POSITIVE LOGITS
     Clo
    0.20
    Blo
    0.20
    ÑĪедÑĪ
    0.19
    vrier
    0.19
     tamp
    0.19
    regor
    0.19
     goede
    0.19
    ä»ĸåıĪ
    0.19
    REEN
    0.18
    setter
    0.18
    Activations Density 0.016%

    No Known Activations