© 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. 16265
    Prev
    Next
    INDEX
    Explanations

    news sections of websites

    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
    enting
    -0.20
    èĦĨå¼±
    -0.19
    afari
    -0.19
    ISCO
    -0.19
    æĤĶ
    -0.19
    gress
    -0.19
    roof
    -0.18
    _COMPANY
    -0.18
    æīŀ
    -0.18
    _intro
    -0.18
    POSITIVE LOGITS
    桨
    0.22
    æ¶Ŀ
    0.21
    æĮŁ
    0.20
    宣å¸ĥ
    0.20
    news
    0.20
    纽
    0.19
    æĸ°éĹ»
    0.19
    çĭĤ
    0.19
    å¸Ĥåľºè§Ħ模
    0.18
    ours
    0.18
    Activations Density 0.009%

    No Known Activations