© 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. 16842
    Prev
    Next
    INDEX
    Explanations

    nanoparticles

    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
    åĴĮåħ¶ä»ĸ
    -0.18
    /fa
    -0.18
    .TypeOf
    -0.18
    åħ¨åĽ½åIJĦåľ°
    -0.18
    âīĤ
    -0.18
     Reflex
    -0.17
     RU
    -0.17
    .jquery
    -0.17
    .lua
    -0.17
    ä¿ļ
    -0.17
    POSITIVE LOGITS
    级åĪ«çļĦ
    0.24
    -scale
    0.23
    尺度
    0.23
    cka
    0.22
    -level
    0.20
    ipop
    0.20
    scale
    0.19
    ì§ľ
    0.19
    _CHIP
    0.19
    éĤ´
    0.19
    Activations Density 0.116%

    No Known Activations