© 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. 1932
    Prev
    Next
    INDEX
    Explanations

    socket.io or network sockets

    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
    utter
    -0.19
    igator
    -0.19
    SCALE
    -0.18
    erk
    -0.18
    nger
    -0.18
     Wilkinson
    -0.18
     titular
    -0.18
    hoff
    -0.18
    orden
    -0.18
    acity
    -0.18
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.37
    ed
    0.28
    ting
    0.24
    UnderTest
    0.22
    gear
    0.21
    edBy
    0.20
    ../../
    0.20
    ivity
    0.20
    ../../../
    0.20
    edImage
    0.20
    Activations Density 0.010%

    No Known Activations