© 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. 16855
    Prev
    Next
    INDEX
    Explanations

    family relationships

    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
    æīĵåĩº
    -0.22
    æĪIJåĵģ
    -0.21
    å®ļçĤ¹
    -0.21
    æµģéĩı
    -0.20
    æµģ
    -0.20
     Flow
    -0.19
    æĹ¥ãĢħ
    -0.19
    æľīéĴĪ对æĢ§
    -0.19
    verity
    -0.19
    åıĪ好
    -0.19
    POSITIVE LOGITS
    çĶŁèĤ²
    0.24
    亲åŃIJ
    0.23
    åħ³ç³»
    0.23
    iblings
    0.23
    aternity
    0.23
    亲å±ŀ
    0.22
    thro
    0.21
    æľªæĪIJå¹´
    0.21
     relationships
    0.21
    æ³ķå®ļ
    0.21
    Activations Density 0.054%

    No Known Activations