© 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. 12166
    Prev
    Next
    INDEX
    Explanations

    older than

    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
    åı¸
    -0.21
    Capability
    -0.20
    ure
    -0.20
    å¼Ĥ常
    -0.19
    æĸ½è¡Į
    -0.19
    ä»Ģä¹Īåı«
    -0.18
    溢
    -0.18
    沫
    -0.18
    éĢĨè¡Į
    -0.17
    ÑĤÑĥÑĢ
    -0.17
    POSITIVE LOGITS
    梦å¢ĥ
    0.20
     Ey
    0.20
    _plural
    0.19
    è··
    0.19
    éģ²
    0.18
     tread
    0.18
     Daw
    0.18
    å±IJ
    0.17
     Controlled
    0.17
     delays
    0.17
    Activations Density 0.002%

    No Known Activations