© 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. 14432
    Prev
    Next
    INDEX
    Explanations

    items in quotes or phrases

    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
     kob
    -0.20
    _lv
    -0.19
    _DLL
    -0.19
    磾
    -0.19
    bjerg
    -0.18
    ILLA
    -0.18
    acades
    -0.18
    çĽĽå¤§
    -0.18
    _fake
    -0.18
    gv
    -0.18
    POSITIVE LOGITS
    åĽ¾æ¡Ī
    0.29
    æŁĦ
    0.28
    é¢ĺæĿIJ
    0.23
    大åѦæ¯ķä¸ļ
    0.22
    çīĪ
    0.21
    åŃĹ
    0.21
    åħ¨å¥Ĺ
    0.21
    -themed
    0.21
    è¡ĮæĶ¿åĮº
    0.20
    åħ¬å®īå±Ģ
    0.20
    Activations Density 0.058%

    No Known Activations