© 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. 11866
    Prev
    Next
    INDEX
    Explanations

    avoiding duplicates or repetition

    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
     scars
    -0.19
    STITUTE
    -0.19
    满äºĨ
    -0.18
    ķĮ
    -0.18
    CDC
    -0.18
    ä»ħ次äºİ
    -0.18
    å¨ł
    -0.18
    èī¯æĢ§
    -0.17
    èijĹ
    -0.17
    Docs
    -0.17
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.23
    lama
    0.22
    ÑıÑģÑĮ
    0.20
    åºŁè¯Ŀ
    0.19
    çıŃ车
    0.19
    å¥Ĺè·¯
    0.19
    unct
    0.19
     stun
    0.18
    大éĿ¢ç§¯
    0.18
    ä¸Ģéģį
    0.18
    Activations Density 0.006%

    No Known Activations