© 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. 13841
    Prev
    Next
    INDEX
    Explanations

    region or regions

    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
    ðŁı»
    -0.23
    ðŁı¼
    -0.21
    åħ¶ä¸Ńä¸Ģ个
    -0.20
    ðŁı½
    -0.18
    åĪ¶åº¦æĶ¹éĿ©
    -0.17
    æł·çļĦ
    -0.17
    heet
    -0.16
    è¡Įéķ¿
    -0.15
     ÅŁekilde
    -0.15
    ðŁı¾
    -0.15
    POSITIVE LOGITS
    ally
    0.37
    åĨħçļĦ
    0.26
    ality
    0.26
    nement
    0.26
    åŁ
    0.25
    wide
    0.23
    -wide
    0.22
    naire
    0.21
    人士
    0.21
    ial
    0.20
    Activations Density 0.038%

    No Known Activations