© 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. 15980
    Prev
    Next
    INDEX
    Explanations

    start of sentence after punctuation

    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
     ÐŁÐ¾Ñĩем
    -0.20
    echo
    -0.19
    è¦ģä¹Ī
    -0.19
    IAS
    -0.19
    åŁĭ
    -0.19
    fold
    -0.19
    TK
    -0.18
    plex
    -0.18
     desk
    -0.18
    GRP
    -0.18
    POSITIVE LOGITS
    éķ¿è¿ľ
    0.21
    èĽĢ
    0.20
    åıĮèµ¢
    0.20
    itus
    0.20
    纡
    0.19
    æĮ¹
    0.19
    éĢłç¦ı
    0.19
    å¢ŀæĶ¶
    0.19
    åĸ
    0.19
    _iface
    0.18
    Activations Density 0.356%

    No Known Activations