© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12363
    Prev
    Next
    INDEX
    Explanations

    nearness or proximity

    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
    .webkit
    -0.19
    æĭIJ
    -0.19
    æѦåĬŁ
    -0.18
    ä¸ŃéĢĶ
    -0.18
    æŃ£å½ĵ
    -0.18
     directions
    -0.18
    æİīäºĨ
    -0.17
    èĭ
    -0.17
     Pok
    -0.17
    direction
    -0.17
    POSITIVE LOGITS
     proximity
    0.35
    è¿ijè·Ŀ离
    0.32
     clos
    0.31
    亲å¯Ĩ
    0.28
     closer
    0.27
    åĴ«
    0.25
    à¹ĥà¸ģล
    0.25
     intimacy
    0.24
    prox
    0.23
    è·ĿéĽ¢
    0.23
    Activations Density 0.050%

    No Known Activations