© 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. 11134
    Prev
    Next
    INDEX
    Explanations

    Kodi tool

    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
    arcer
    -0.20
    prov
    -0.19
    秩
    -0.19
    sPid
    -0.19
    VMLINUX
    -0.19
    éľ²åĩº
    -0.18
    åĵªåĦ¿
    -0.18
    æĽĿ
    -0.18
    临æŶ
    -0.18
    çªģ
    -0.18
    POSITIVE LOGITS
    åħ¶éĹ´
    0.23
     Nose
    0.20
     Telegraph
    0.19
    æ·Ļ
    0.19
    æľŁéĸĵ
    0.19
    rot
    0.18
     notes
    0.18
     leash
    0.18
    ç¥ļ
    0.18
    åĨ¢
    0.17
    Activations Density 0.001%

    No Known Activations