© 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. 16860
    Prev
    Next
    INDEX
    Explanations

    total of

    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
    楼主
    -0.20
    è¡·
    -0.20
     Hwy
    -0.19
    ëŁ¼
    -0.18
    çļĦéĩįçĤ¹
    -0.18
    æĢİèĥ½
    -0.18
    å°ıå¿ĥ
    -0.18
    âĻ¬
    -0.18
    .Automation
    -0.18
     Msg
    -0.17
    POSITIVE LOGITS
    大æ¦Ĥæĺ¯
    0.23
    ãģ¼
    0.21
     longtime
    0.20
     nonatomic
    0.20
    éĹ®ä»ĸ
    0.20
    ä¸İæѤåIJĮæŶ
    0.19
    æľīä¸Ģç§į
    0.19
    åĮĹ京大åѦ
    0.19
     fucks
    0.19
    åĵĪä½Ľ
    0.18
    Activations Density 0.078%

    No Known Activations