© 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. 11721
    Prev
    Next
    INDEX
    Explanations

    comprehensive followed by descriptive noun

    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
    éĩįè¦ģæĦıä¹ī
    -0.18
    inke
    -0.18
    toy
    -0.17
    pired
    -0.17
    à¹Ģà¸Ħ
    -0.17
    avier
    -0.17
    ä¸Ģç§į
    -0.17
    è¿Ļ个æŶåĢĻ
    -0.16
    spot
    -0.16
    éĩįè¦ģä½ľçĶ¨
    -0.16
    POSITIVE LOGITS
    ç»Ĩèĩ´
    0.27
    zza
    0.21
     enough
    0.20
    详ç»ĨçļĦ
    0.18
    /ext
    0.18
    -minded
    0.18
    -ranging
    0.17
    çłĶ究表æĺİ
    0.17
    æĢ§çļĦ
    0.17
    /exp
    0.17
    Activations Density 0.028%

    No Known Activations