© 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. 10891
    Prev
    Next
    INDEX
    Explanations

    save game state

    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
    èĤĮ
    -0.22
    è¡¿
    -0.21
     Ñĥзн
    -0.20
    ’acc
    -0.20
    èĬį
    -0.19
     fac
    -0.18
    =form
    -0.18
    _algo
    -0.17
     Colomb
    -0.17
     wider
    -0.17
    POSITIVE LOGITS
    ä½ĵåĬĽ
    0.24
    é»ijæļĹ
    0.23
    æĤ¬å´ĸ
    0.23
     наÑĢко
    0.22
    æ¯ıä¸Ģ天
    0.21
    agos
    0.21
    人çī©
    0.21
    æŃ»äº¡
    0.21
    enu
    0.20
    nex
    0.20
    Activations Density 0.025%

    No Known Activations