© 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. 13331
    Prev
    Next
    INDEX
    Explanations

    photo contest

    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
    ÅĤów
    -0.19
    lessness
    -0.19
    _ComCallableWrapper
    -0.18
    unity
    -0.18
    assin
    -0.18
    elite
    -0.18
    áĢī
    -0.18
    cip
    -0.18
    ÅŁÄ±
    -0.18
     DirectoryInfo
    -0.17
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.21
    çī¹éĤĢ
    0.20
    ä¸Ģæīĭ
    0.20
     idea
    0.19
     palm
    0.19
    å½±åĥı
    0.19
    ä¸ĬæĬ¥
    0.18
    ter
    0.18
    çĶ°éĩİ
    0.18
     pictures
    0.18
    Activations Density 0.001%

    No Known Activations