© 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. 16269
    Prev
    Next
    INDEX
    Explanations

    will be gone by

    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
    ç§ģ
    -0.20
     yesterday
    -0.19
    ients
    -0.19
    Yesterday
    -0.19
     priv
    -0.19
    æľ¬åij¨
    -0.18
     spontaneous
    -0.18
    ÇĴ
    -0.18
    æĺ¨æĹ¥
    -0.18
    åľ¨æł¡
    -0.18
    POSITIVE LOGITS
    åĿł
    0.24
    å±ĬæŶ
    0.23
    æ·±è¿ľ
    0.23
     someday
    0.22
    estone
    0.21
    ucz
    0.21
    å°Ĩè¾¾åĪ°
    0.20
    对ä¸ŃåĽ½
    0.20
    å°Ĩä¼ļ
    0.20
    quirer
    0.19
    Activations Density 0.011%

    No Known Activations