© 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. 13554
    Prev
    Next
    INDEX
    Explanations

    video content

    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
     Paperback
    -0.20
    æħ¨
    -0.20
    游æĪıè£ħå¤ĩ
    -0.19
    æľ¬æĬ¥
    -0.18
    _arrays
    -0.18
    ä¼ı
    -0.18
    æİ¥èijĹ
    -0.18
    èĤ¼
    -0.18
    _TLS
    -0.18
     Comic
    -0.18
    POSITIVE LOGITS
    è§Ĩé¢ij
    0.59
     video
    0.54
     videos
    0.49
    å½ķåĥı
    0.49
    video
    0.48
     footage
    0.42
     vidéo
    0.42
    -video
    0.41
    å½ķåĪ¶
    0.41
    å½ķ
    0.40
    Activations Density 0.308%

    No Known Activations