© 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. 12550
    Prev
    Next
    INDEX
    Explanations

    remains and remnants of something

    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
    é©Ń
    -0.20
    åŀĮ
    -0.18
    æĹłæ¯Ķ
    -0.18
    æĸ°å¸¸æĢģ
    -0.17
    lya
    -0.17
    çĭİ
    -0.17
     оÑģоб
    -0.17
    пиÑģаÑĤÑĮ
    -0.17
    ivate
    -0.16
     thÄĥm
    -0.16
    POSITIVE LOGITS
    æ®ĭçķĻ
    0.27
    æ®ĭ
    0.26
     remnants
    0.23
    åī©
    0.21
     traces
    0.20
    acle
    0.20
     residual
    0.18
    æ®ĺ
    0.18
    骸
    0.18
     leftover
    0.18
    Activations Density 0.033%

    No Known Activations