© 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. 1721
    Prev
    Next
    INDEX
    Explanations

    Hilton, Hilti, Hilbert, Stilton

    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
    inality
    -0.23
    ILITY
    -0.20
     opi
    -0.19
    eness
    -0.19
     bile
    -0.18
    ãģĦãĤĭ
    -0.18
    gers
    -0.18
    usterity
    -0.18
    OperationException
    -0.17
    ertools
    -0.17
    POSITIVE LOGITS
    fork
    0.21
    ÙĨاÙĨ
    0.20
     deferred
    0.20
    ãģĵãģ¨
    0.19
    Drawable
    0.19
    fort
    0.19
    perc
    0.19
    kok
    0.18
    ingly
    0.18
     hall
    0.18
    Activations Density 0.003%

    No Known Activations