© 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. 16945
    Prev
    Next
    INDEX
    Explanations

    tagged with

    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
    梯
    -0.23
    èĮ
    -0.21
    æ´¾
    -0.20
    Åļ
    -0.20
    went
    -0.19
    à¸Ħà¸ĵะà¸ģรรม
    -0.19
    AFE
    -0.19
     Colo
    -0.18
     UObject
    -0.18
    为
    -0.18
    POSITIVE LOGITS
    éķ¿éķ¿
    0.23
    iếc
    0.23
    ç¼ĿéļĻ
    0.22
    æīĭåĬ¿
    0.20
    èĥ¯
    0.20
    toMatch
    0.19
    èµ·è¯ī
    0.19
    赶ä¸Ĭ
    0.19
     milfs
    0.19
    æī©æķ£
    0.18
    Activations Density 0.010%

    No Known Activations