© 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. 14044
    Prev
    Next
    INDEX
    Explanations

    kin, Luis, Arkin, film, retirement, Registered

    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
    害ç¾ŀ
    -0.23
    ãģ¡ãĤĩãģĨ
    -0.22
     мÑıг
    -0.21
    NCY
    -0.21
    éª
    -0.20
    åĩºæ±Ĺ
    -0.20
    磸
    -0.20
    erce
    -0.19
    _SLOT
    -0.19
    è¢į
    -0.18
    POSITIVE LOGITS
    åħ¨åijĺ
    0.29
    æĬ¥èѦ
    0.25
    çİ°åľº
    0.23
    çĶµå½±
    0.22
    æ³°å±±
    0.21
     exter
    0.21
    å°ĸåı«
    0.21
    人æķ°
    0.21
    ç»Ħ
    0.21
    å¤ļ人
    0.21
    Activations Density 0.032%

    No Known Activations