© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15110
    Prev
    Next
    INDEX
    Explanations

    p38-dependent pathway

    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
    æī¾äºĨ
    -0.23
    ApplicationBuilder
    -0.20
    çĶŁæ´»çݯå¢ĥ
    -0.19
    榫
    -0.19
    echa
    -0.18
    åĬłåĢį
    -0.18
    å¯Įè´µ
    -0.18
    _PARAMETER
    -0.17
    大大å°ı
    -0.17
    æ¦
    -0.17
    POSITIVE LOGITS
    dependent
    0.20
    opensource
    0.20
    Tester
    0.19
    manda
    0.19
     metav
    0.18
    ä¸įéĢļ
    0.18
    ama
    0.18
    iso
    0.18
     alone
    0.18
    ·æĸ°
    0.18
    Activations Density 0.407%

    No Known Activations