© 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. 11646
    Prev
    Next
    INDEX
    Explanations

    voluntary actions and contexts

    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
    åĭį
    -0.20
    们çļĦ
    -0.19
    plied
    -0.18
    åĢij
    -0.18
    wards
    -0.17
     اÙĦسÙĨ
    -0.17
    glyph
    -0.17
    äºĨ解åĪ°
    -0.17
    æĦ¿æĦı
    -0.16
    符
    -0.16
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.21
    клон
    0.18
    mente
    0.18
    seau
    0.18
    WithPath
    0.18
    itas
    0.17
    áºŃp
    0.17
    yyy
    0.17
    笥
    0.17
    ness
    0.17
    Activations Density 0.003%

    No Known Activations