© 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. 13761
    Prev
    Next
    INDEX
    Explanations

    shipping services, fonts, program names

    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
    ime
    -0.20
    å±¥
    -0.19
    osos
    -0.19
    ç£ķ
    -0.19
    inee
    -0.18
    izen
    -0.18
    ase
    -0.18
    .Fore
    -0.18
    å¼Ħ
    -0.18
    åĬĿ
    -0.18
    POSITIVE LOGITS
    æĪŁ
    0.21
    æĸ¹å¼ıè¿Ľè¡Į
    0.21
    æĹłæīĢè°ĵ
    0.20
    ä¸Ńå°ıåѦ
    0.20
     octave
    0.20
    为ä»Ģä¹Īä¼ļ
    0.20
    æĪĸåħ¶ä»ĸ
    0.20
    ä¸įå¦Ĥ
    0.20
    ìĺ
    0.20
    çIJ¬
    0.20
    Activations Density 0.004%

    No Known Activations