© 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. 15879
    Prev
    Next
    INDEX
    Explanations

    element deficiency and status

    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
    æĭĨ
    -0.28
    注å®ļ
    -0.21
    æ³ķå¾ĭ责任
    -0.20
    æĶ¹è£ħ
    -0.19
    erville
    -0.19
    æĴķ
    -0.19
    ÇŃ
    -0.19
    æīįåıijçİ°
    -0.18
    åijIJ
    -0.18
    olio
    -0.18
    POSITIVE LOGITS
    MBER
    0.21
     subs
    0.20
     Carlson
    0.19
     Ø£ÙĩÙħ
    0.18
     important
    0.18
    åŃ
    0.18
    Dar
    0.18
    çĦī
    0.18
    .Roles
    0.18
     hy
    0.17
    Activations Density 0.036%

    No Known Activations