© 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. 13158
    Prev
    Next
    INDEX
    Explanations

    Dixon, Sinclair, Dominion, Donovan

    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
    lessly
    -0.19
    èij¡
    -0.18
    bor
    -0.18
     Regents
    -0.17
    ness
    -0.17
    ªĮ
    -0.16
     gist
    -0.16
    kins
    -0.16
    avers
    -0.16
    æĸ°å¾ģç¨ĭ
    -0.15
    POSITIVE LOGITS
    ally
    0.20
    åŀ©
    0.17
    ality
    0.17
    oodle
    0.17
    hä
    0.17
    .annotate
    0.17
    arily
    0.16
    ä¼Ļä¼´åħ³ç³»
    0.16
    à¸ĵ
    0.16
    pute
    0.15
    Activations Density 0.003%

    No Known Activations