© 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. 1808
    Prev
    Next
    INDEX
    Explanations

    antenna and outdoor equipment

    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
     trilogy
    -0.27
    менÑĤ
    -0.25
    events
    -0.25
    mere
    -0.24
    صÙĨد
    -0.23
    对è¯Ŀ
    -0.23
    _occ
    -0.23
     Blanc
    -0.23
     Prelude
    -0.23
    _events
    -0.23
    POSITIVE LOGITS
     antenna
    0.40
     weather
    0.37
    /weather
    0.35
     Weather
    0.35
    室å¤ĸ
    0.33
     antennas
    0.33
     outdoor
    0.33
    梢
    0.32
    Weather
    0.32
    weather
    0.31
    Activations Density 0.108%

    No Known Activations