© 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. 15619
    Prev
    Next
    INDEX
    Explanations

    unlimited use

    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
    ÑĢÑĥÑĩ
    -0.23
    åĽ¡
    -0.19
    çļĦæĪIJåĬŁ
    -0.19
     tal
    -0.18
    aven
    -0.18
    åѤç«ĭ
    -0.18
    èŁ¹
    -0.18
    èĥ½åģļåĪ°
    -0.18
    æݨåĩºäºĨ
    -0.18
     irrational
    -0.18
    POSITIVE LOGITS
     unlimited
    0.30
    æĹłéĻIJ
    0.28
     Unlimited
    0.22
    ä¸įéĻIJ
    0.21
    çķħ
    0.21
    æĿĥ
    0.20
    æľŁåĨħ
    0.20
    次æķ°
    0.20
    æĹ©æĻļ
    0.19
    rox
    0.19
    Activations Density 0.025%

    No Known Activations