© 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. 14865
    Prev
    Next
    INDEX
    Explanations

    reporting what someone said

    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
    注å®ļ
    -0.22
    羣æŃ£åģļåĪ°
    -0.19
    éĻ¤åİ»
    -0.19
    æĪijä¸Ģ缴
    -0.19
    赶ä¸Ĭ
    -0.18
    anker
    -0.18
    íĥľ
    -0.18
    Reviewed
    -0.18
    èĭ¦èĭ¦
    -0.17
     полÑĥÑĩа
    -0.17
    POSITIVE LOGITS
     also
    0.27
    æĮĩåĩº
    0.25
    è¿
    0.23
    also
    0.23
    çļĦçIJĨçĶ±
    0.22
    èijŃ
    0.22
    åIJĮæĹ¶ä¹Ł
    0.22
     ÑĤакже
    0.22
     further
    0.21
    éļıåį³
    0.21
    Activations Density 0.035%

    No Known Activations