© 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. 14078
    Prev
    Next
    INDEX
    Explanations

    in creating actions

    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
    åľ¨è¿Ļç§į
    -0.24
    缴åĪ°
    -0.23
    ä¸Ģ缴åĪ°
    -0.22
    åĽłä¸ºåľ¨
    -0.22
    åľ¨åĨħçļĦ
    -0.21
    åľ¨æĦı
    -0.20
    æį®æѤ
    -0.20
    ĵåIJį
    -0.20
    æ°´åĩĨ
    -0.19
    è¶ģ
    -0.18
    POSITIVE LOGITS
    ÑģÑĮ
    0.23
    è¿ĩç¨ĭä¸Ń
    0.23
    çļĦè¿ĩç¨ĭä¸Ń
    0.23
     endeavor
    0.21
    ç°Į
    0.21
    è¿ĩç¨ĭå½ĵä¸Ń
    0.20
    bett
    0.20
    éģİç¨ĭä¸Ń
    0.19
    çĺ°
    0.19
    åıijçİ°èĩªå·±
    0.18
    Activations Density 0.083%

    No Known Activations