© 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. 16517
    Prev
    Next
    INDEX
    Explanations

    footage from and after

    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
    ows
    -0.21
    çĽı
    -0.19
    innen
    -0.19
    ships
    -0.18
    们éĥ½
    -0.18
    ToMany
    -0.18
    à¹Į
    -0.17
    棵æłij
    -0.17
    -être
    -0.17
    à¹Ĩ
    -0.17
    POSITIVE LOGITS
    hai
    0.21
    ordon
    0.20
    oling
    0.18
    auge
    0.18
    phere
    0.18
    ILLE
    0.17
    Inicial
    0.16
    ource
    0.16
    immer
    0.16
    edo
    0.16
    Activations Density 0.003%

    No Known Activations