© 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. 14453
    Prev
    Next
    INDEX
    Explanations

    restore from backup

    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
    andin
    -0.21
     ho
    -0.20
    "urls
    -0.20
    mma
    -0.19
    CALLTYPE
    -0.19
    社交
    -0.19
    ðŁĶĮ
    -0.19
    krä
    -0.19
    ghan
    -0.19
    elters
    -0.19
    POSITIVE LOGITS
    æģ¢å¤į
    0.32
     restore
    0.29
    è¿ĺåİŁ
    0.27
    restore
    0.26
    Restore
    0.25
     restores
    0.24
    æģ¢
    0.24
     recovery
    0.24
     dataSnapshot
    0.23
    .restore
    0.23
    Activations Density 0.070%

    No Known Activations