© 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. 16172
    Prev
    Next
    INDEX
    Explanations

    show bar, show case, show biz, show room

    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
    æ·±å¤Ħ
    -0.20
    amer
    -0.17
    åħīèį£
    -0.17
    shoot
    -0.16
    åĬŀåħ¬åİħ
    -0.16
    æ·±åİļ
    -0.16
    åİļåİļçļĦ
    -0.16
    éĤ£ä¸ªäºº
    -0.15
     Eve
    -0.15
    å°ıåºĹ
    -0.15
    POSITIVE LOGITS
    manship
    0.23
    çĴ¨
    0.19
    antha
    0.17
    æĭĪ
    0.17
    ç¾°
    0.17
    èĩ³äºİ
    0.17
    åħ¶ä½Ļ
    0.17
    ãģĹãģı
    0.16
    -winning
    0.16
    /animations
    0.16
    Activations Density 0.033%

    No Known Activations