© 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. 14418
    Prev
    Next
    INDEX
    Explanations

    unused or inactive items

    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
    /Main
    -0.22
    è¡·
    -0.20
    /Runtime
    -0.19
    纵深
    -0.19
    usual
    -0.19
    主é¢ĺ
    -0.19
    _erase
    -0.18
    ç»İ
    -0.18
    ç»®
    -0.18
    èĥ¸æĢĢ
    -0.18
    POSITIVE LOGITS
    éĹ²ç½®
    0.38
     unused
    0.30
    æIJģ
    0.28
    unused
    0.26
     inactive
    0.26
    Unused
    0.25
    æĺİçıł
    0.25
    åŃĺæĶ¾
    0.23
    å¼ĥ
    0.23
     unus
    0.23
    Activations Density 0.061%

    No Known Activations