© 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. 15894
    Prev
    Next
    INDEX
    Explanations

    blog URLs

    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
    èİ·
    -0.24
    æ´¼
    -0.21
    æĺ¯ä»ĸ
    -0.21
    ä»
    -0.20
    è§Ħ磩
    -0.19
    寸
    -0.19
    è´´
    -0.19
     ÐĶмиÑĤÑĢ
    -0.18
    æĬ¥
    -0.18
    благо
    -0.18
    POSITIVE LOGITS
    éĽī
    0.20
     iNdEx
    0.20
     ÑĤоÑĢ
    0.19
    çIJ¬
    0.19
    oste
    0.19
    ubb
    0.18
    ModelProperty
    0.18
    ibilities
    0.18
    _nth
    0.18
    èijĨ
    0.18
    Activations Density 0.071%

    No Known Activations