© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2160
    Prev
    Next
    INDEX
    Explanations

    Formula 1 teams, racing, and trials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    pile
    -0.27
    è°¯
    -0.24
    atto
    -0.23
    EXT
    -0.23
     acknowled
    -0.23
    ÑħодиÑĤÑĮ
    -0.22
     discharged
    -0.22
    ied
    -0.22
    FromFile
    -0.22
    utter
    -0.22
    POSITIVE LOGITS
     Confidential
    0.26
    ç§ijæĬĢèĤ¡ä»½
    0.23
     yap
    0.23
    <tbody
    0.23
    ç²Ĺç³Ļ
    0.23
    antro
    0.22
    çĭ¬å®¶
    0.22
     bench
    0.22
    elage
    0.21
     BUG
    0.21
    Activations Density 0.004%

    No Known Activations