© 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. 1898
    Prev
    Next
    INDEX
    Explanations

    programming imports and definitions

    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
    LETTE
    -0.27
    oter
    -0.26
    _flutter
    -0.24
    Pressed
    -0.24
    esses
    -0.24
    ogram
    -0.23
    illing
    -0.23
     nhi
    -0.23
    .decorate
    -0.23
    izont
    -0.23
    POSITIVE LOGITS
     Moderator
    0.25
     awesome
    0.24
    åĽ¾æĸĩ
    0.24
     Official
    0.23
     moderator
    0.23
    :j
    0.23
     Reviews
    0.23
    sar
    0.22
    zan
    0.22
    è´´åIJ§
    0.22
    Activations Density 0.002%

    No Known Activations