© 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. 14611
    Prev
    Next
    INDEX
    Explanations

    email address

    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
    ä¸įäºĨ
    -0.23
    lining
    -0.21
    æĤ±
    -0.20
     defer
    -0.20
    èī¯
    -0.20
    çĩ¥
    -0.19
     ME
    -0.18
    Mark
    -0.18
     approvals
    -0.18
     tre
    -0.18
    POSITIVE LOGITS
    wizard
    0.24
    举è¡ĮäºĨ
    0.23
    æī¾åĽŀ
    0.23
    è¯ģ件
    0.22
     Orth
    0.20
    举è¡Į
    0.19
    LowerCase
    0.19
    å®ļéĩı
    0.19
    éļĨéĩį举è¡Į
    0.19
    æģŃåĸľ
    0.18
    Activations Density 0.034%

    No Known Activations