© 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. 15516
    Prev
    Next
    INDEX
    Explanations

    Copper Cliff

    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
    oot
    -0.21
    anko
    -0.20
    unan
    -0.20
     vi
    -0.19
    adic
    -0.18
    GMEM
    -0.18
    çĥĤ
    -0.18
    ukkan
    -0.18
    æ³½
    -0.18
     Meyer
    -0.18
    POSITIVE LOGITS
    ighborhood
    0.22
     Introduced
    0.21
    ä¾ĥ
    0.20
    Introduced
    0.19
    BuilderInterface
    0.19
    -modules
    0.19
    è¿Ļ两ç§į
    0.19
     variants
    0.18
    说æĺİ书
    0.18
    éĴ¹
    0.18
    Activations Density 0.034%

    No Known Activations