© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10597
    Prev
    Next
    INDEX
    Explanations

    advanced stages, emergencies, notice, later

    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
    æĮģä¹ħ
    -0.22
    è½½
    -0.21
     früh
    -0.20
     sectional
    -0.19
    åĩºæĿ¥äºĨ
    -0.19
    éķ¿çĽ¸
    -0.18
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.18
     expert
    -0.18
     persistent
    -0.18
    ç§įç§į
    -0.18
    POSITIVE LOGITS
    æĥ³èµ·
    0.20
    fw
    0.19
    åıªåī©
    0.19
    临
    0.19
    èĩ¨
    0.19
    è¡¥
    0.18
    å¾Ģå¤ĸ
    0.18
    _fail
    0.18
     imitation
    0.18
    åķľ
    0.18
    Activations Density 0.024%

    No Known Activations