© 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. 14021
    Prev
    Next
    INDEX
    Explanations

    (PRWEB) /PRNewswire/ --

    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
    VEL
    -0.20
    cratch
    -0.19
     Rough
    -0.18
    .CreateCommand
    -0.17
     Ike
    -0.17
    ero
    -0.17
    ç¹ģèį£
    -0.17
    há»ķ
    -0.17
    OTS
    -0.17
    èĨĬ
    -0.17
    POSITIVE LOGITS
     cof
    0.21
    æī§ä¸ļ
    0.20
    æ±Łè¥¿
    0.20
    INI
    0.19
    çĻ¾åIJĪ
    0.19
    æĥ³æĥ³
    0.19
     sop
    0.18
     ÑģоÑģ
    0.18
    isions
    0.18
    åķĦ
    0.18
    Activations Density 0.008%

    No Known Activations