© 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. 15544
    Prev
    Next
    INDEX
    Explanations

    openly transgender

    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
    iators
    -0.18
    ç¾İå¾·
    -0.18
    åĮ¡
    -0.18
    仵
    -0.18
    _scr
    -0.18
    ило
    -0.17
     меÑĢ
    -0.17
    Scr
    -0.17
     Genuine
    -0.17
    åıªè¦ģä½ł
    -0.17
    POSITIVE LOGITS
    aji
    0.21
    andre
    0.20
    aye
    0.20
    ä¸»å¼ł
    0.19
    issement
    0.18
    Disclosure
    0.18
    çīĮ
    0.18
    ï¸
    0.18
    对æĪij说
    0.18
    IME
    0.18
    Activations Density 0.009%

    No Known Activations