© 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. 12182
    Prev
    Next
    INDEX
    Explanations

    to say, to blame, to like

    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
    è¿ľ
    -0.21
    称
    -0.20
    å¾®å¦Ļ
    -0.20
    æ´»
    -0.19
    ambda
    -0.19
    _RESP
    -0.19
    _trap
    -0.18
    åĬ¡
    -0.18
    åħīæĺİ
    -0.18
    åIJ¸
    -0.18
    POSITIVE LOGITS
    京津
    0.20
    å·¡åĽŀ
    0.19
    å·¡è§Ĩ
    0.18
    /mp
    0.18
    aal
    0.18
    髹
    0.17
    ç¼ī
    0.17
    è°ĥåīĤ
    0.17
     unarmed
    0.17
    çİ«
    0.17
    Activations Density 1.064%

    No Known Activations