© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    Easter related phrases

    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
    ä¿ĿèįIJ
    -0.22
    éĵĤ
    -0.20
    sets
    -0.20
    åīįèĢħ
    -0.19
    åIJİèĢħ
    -0.19
    iren
    -0.19
    itaire
    -0.19
    sys
    -0.19
    imps
    -0.19
     Vanderbilt
    -0.19
    POSITIVE LOGITS
    ivals
    0.24
    ITES
    0.24
    pillar
    0.23
    mente
    0.23
    åĪ¸
    0.22
    æĿ¥ä¸´
    0.21
    most
    0.21
    lies
    0.20
    wards
    0.20
    oola
    0.20
    Activations Density 0.005%

    No Known Activations