© 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. 13210
    Prev
    Next
    INDEX
    Explanations

    countries and cities

    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
    $core
    -0.21
    anke
    -0.20
    æĪijæĥ³
    -0.20
     thrill
    -0.20
    Wildcard
    -0.19
    _mu
    -0.19
    /swagger
    -0.19
    ircon
    -0.18
    (real
    -0.18
    éĩİçĶŁ
    -0.18
    POSITIVE LOGITS
    éĥ½ä¸įæķ¢
    0.21
    animate
    0.21
    Pok
    0.19
     Peg
    0.19
    èĪħ
    0.18
     peg
    0.18
    å±ı
    0.18
    ç¤
    0.17
     wag
    0.17
     Kelley
    0.17
    Activations Density 0.333%

    No Known Activations