© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    xml tags and programming syntax

    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
     (::
    -0.24
    ãĢģ“
    -0.23
     Hick
    -0.23
     RESET
    -0.23
     "`
    -0.23
     Kurd
    -0.22
     "...
    -0.22
     ::=
    -0.22
    éļĺ
    -0.22
     <<<
    -0.22
    POSITIVE LOGITS
    allen
    0.23
    idor
    0.23
     SimpleName
    0.22
    /linux
    0.21
     shedding
    0.21
    ä»ķ
    0.21
     Neg
    0.21
     april
    0.20
    åĿĿ
    0.20
     themselves
    0.20
    Activations Density 1.584%

    No Known Activations