© 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. 16588
    Prev
    Next
    INDEX
    Explanations

    directions and bearings

    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
    å¹´éĻIJ
    -0.22
    åįĥå¹´
    -0.20
    ä¸İåıijå±ķ
    -0.20
    åĢļ
    -0.19
     SCR
    -0.18
    äºĶè¡Į
    -0.18
     Recover
    -0.18
    纵深
    -0.17
     scratch
    -0.17
    çĦ
    -0.17
    POSITIVE LOGITS
    alian
    0.20
     çık
    0.19
    Mate
    0.19
    åĪĽæĸ°åŀĭ
    0.18
     Berm
    0.18
     thermometer
    0.18
    çļĦä¸ľè¥¿
    0.18
    è¿Ļ个æĹ¶ä»£
    0.18
    EAR
    0.17
    è´§æŀ¶
    0.17
    Activations Density 0.003%

    No Known Activations