© 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. 16508
    Prev
    Next
    INDEX
    Explanations

    TweetDeck or email clients

    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
     игÑĢов
    -0.22
    éĻĦ
    -0.21
    éĵ¿
    -0.19
    override
    -0.19
    ä½ľåĵģåĨħ容
    -0.19
    ä¸ŃåĽ½ç»ıæµİ
    -0.19
     lider
    -0.19
     abuse
    -0.19
    ç¯ĩç«ł
    -0.18
     mer
    -0.18
    POSITIVE LOGITS
    泡
    0.20
    rello
    0.20
    	ui
    0.20
    ÐĵÐŀ
    0.19
    ä¹łæĥ¯
    0.18
    社交
    0.18
    coni
    0.18
    -cli
    0.18
    habit
    0.17
     ui
    0.17
    Activations Density 0.040%

    No Known Activations