© 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. 16201
    Prev
    Next
    INDEX
    Explanations

    sleep, nap, rest, asleep

    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
    æħµ
    -0.23
    庸
    -0.22
    ä¸Ģéĥ¨
    -0.21
    æĹ·
    -0.21
    æĩĴ
    -0.19
    æ®ĭ
    -0.19
    箸
    -0.19
    éĵŃè®°
    -0.18
    çĽijçĭ±
    -0.18
    _idle
    -0.18
    POSITIVE LOGITS
    å³Ĵ
    0.21
    è¯Ĥ
    0.21
    åľ¨å¹¿å·ŀ
    0.20
    ä¸ĭæĿ¥
    0.18
     ké
    0.18
    ç©¿
    0.18
    adol
    0.18
    ilos
    0.18
    èħ¾
    0.17
    åĩºè¡Į
    0.17
    Activations Density 0.006%

    No Known Activations