© 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. 16377
    Prev
    Next
    INDEX
    Explanations

    abstract nouns and lists

    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
    endir
    -0.20
    evity
    -0.19
    berger
    -0.19
    âĦĹ
    -0.19
    dale
    -0.19
    astos
    -0.19
    ician
    -0.18
    .av
    -0.18
     !***
    -0.17
    è¿Ļ件
    -0.17
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.26
    çŃīæĸ¹å¼ı
    0.25
    çŃīå½¢å¼ı
    0.24
    -type
    0.22
    æ¯Ķå¦Ĥ
    0.21
    æĪĸ
    0.21
    ç±»
    0.21
    åŀĭ
    0.21
    诸å¦Ĥ
    0.20
     worn
    0.20
    Activations Density 0.165%

    No Known Activations