© 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. 2151
    Prev
    Next
    INDEX
    Explanations

    lists with names and abbreviations

    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
    çī¹åĪ«æĺ¯åľ¨
    -0.25
    éĩ
    -0.25
    '},č↵
    -0.23
    emies
    -0.22
    **č↵
    -0.22
    ...",↵
    -0.22
    ...',↵
    -0.22
    们çļĦ
    -0.22
    ----------č↵
    -0.22
    oning
    -0.22
    POSITIVE LOGITS
    çĭ¬æľīçļĦ
    0.23
     Epoch
    0.23
    çĮĹ
    0.22
    Powered
    0.21
    edb
    0.21
    Untitled
    0.21
     copyrighted
    0.21
     deter
    0.21
    prototype
    0.21
    /Open
    0.21
    Activations Density 0.335%

    No Known Activations