© 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. 15073
    Prev
    Next
    INDEX
    Explanations

    copyright notices or code comments

    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
    lug
    -0.21
    LOWER
    -0.20
    LEG
    -0.19
    ડ
    -0.18
    ountain
    -0.18
    stration
    -0.18
    ToFit
    -0.18
    arez
    -0.18
    .jet
    -0.18
    ortal
    -0.18
    POSITIVE LOGITS
    rete
    0.23
    (Parcel
    0.20
     Giuliani
    0.19
    åĬłåĽº
    0.19
    åIJij社ä¼ļ
    0.19
    åĬ©çIJĨ
    0.19
    游æĪıå½ĵä¸Ń
    0.18
    åĢ¬
    0.18
    åIJİåĨį
    0.18
    åıĹçģ¾
    0.18
    Activations Density 0.001%

    No Known Activations