© 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. 14460
    Prev
    Next
    INDEX
    Explanations

    power over

    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
    otten
    -0.21
    åħīèĬĴ
    -0.20
    ozo
    -0.20
    auce
    -0.19
    okie
    -0.19
    esses
    -0.19
    /request
    -0.18
    adian
    -0.18
    amed
    -0.17
    ams
    -0.17
    POSITIVE LOGITS
    éĹ®é¢ĺæĺ¯
    0.23
    éĥ¨åī¯
    0.21
    æĸ¹éĿ¢çļĦ
    0.20
    æĸ¹å¼ı
    0.18
    æĪijåıªæĺ¯
    0.17
    åĻ¨
    0.17
    åĮĸè¿Ľç¨ĭ
    0.17
    æĹłå¿§
    0.17
    设å¤ĩ
    0.17
     Pickup
    0.17
    Activations Density 0.028%

    No Known Activations