© 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. 15592
    Prev
    Next
    INDEX
    Explanations

    tide, shallow, tidal

    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
     spinning
    -0.22
     viên
    -0.21
    éĽªèĬ±
    -0.21
    æı©
    -0.21
    å°ĺ
    -0.21
     Dust
    -0.20
     spun
    -0.20
    -spin
    -0.20
    é£ĺ
    -0.20
    erosis
    -0.20
    POSITIVE LOGITS
    涨
    0.25
    ped
    0.23
    éĢĢ
    0.23
    èĪĦ
    0.22
    为人
    0.22
    为åĩĨ
    0.21
    æµħ
    0.21
    ä¿Ŀè¯ģéĩij
    0.21
    Platforms
    0.21
    æ¹Ħ
    0.21
    Activations Density 0.025%

    No Known Activations