© 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. 16283
    Prev
    Next
    INDEX
    Explanations

    importance and usefulness

    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
    PropertyParams
    -0.25
    æĭīå¼Ģ
    -0.19
    ä»Ģä¹Īä¸ľè¥¿
    -0.19
    umbs
    -0.19
    çek
    -0.18
    عة
    -0.18
    urname
    -0.18
    åłĥ
    -0.18
    getRoot
    -0.18
    NdEx
    -0.18
    POSITIVE LOGITS
    åĪĨåĪ«æĺ¯
    0.22
    诸å¦Ĥ
    0.20
    fall
    0.20
     ici
    0.20
    鸢
    0.19
    here
    0.19
    åħĪåIJİ
    0.19
     here
    0.18
    Anchor
    0.18
     namely
    0.18
    Activations Density 0.135%

    No Known Activations