© 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. 15711
    Prev
    Next
    INDEX
    Explanations

    Shiva or vim

    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
    ather
    -0.21
    ãģĹãĤĩãģĨ
    -0.20
    Ñĩа
    -0.20
    ма
    -0.18
    ation
    -0.18
    æĬķèµĦ人
    -0.18
    èĥ¥
    -0.17
    agement
    -0.17
    hes
    -0.17
    æĢ
    -0.17
    POSITIVE LOGITS
    oxy
    0.22
     bidi
    0.21
    foundation
    0.20
     Ñģебе
    0.19
    亡
    0.18
    enci
    0.18
    æĶ¹éĢł
    0.17
     Tribune
    0.17
    æıŃ
    0.17
    ideo
    0.17
    Activations Density 0.002%

    No Known Activations