© 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. 16014
    Prev
    Next
    INDEX
    Explanations

    application, deposition, spray, print, coating

    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
    ooks
    -0.21
    æī¾åĽŀ
    -0.20
    /ns
    -0.20
     Selling
    -0.19
    egt
    -0.18
    unde
    -0.18
    æĭ³
    -0.18
    èĨij
    -0.18
    InOut
    -0.18
    alist
    -0.18
    POSITIVE LOGITS
    ÑĢÑĥÑĩ
    0.26
     onto
    0.23
    åijĺ
    0.22
    éĩı
    0.21
    é£ŀæī¬
    0.20
    è½½ä½ĵ
    0.20
     deposition
    0.20
    æ´ĭæ´ĭ
    0.20
    åĪĨéħį
    0.20
     dro
    0.20
    Activations Density 0.105%

    No Known Activations