© 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. 2635
    Prev
    Next
    INDEX
    Explanations

    Formula 1 Grand Prix

    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
     USDA
    -0.38
     statewide
    -0.32
     FEMA
    -0.32
     Appalachian
    -0.30
     Connecticut
    -0.30
     Arkansas
    -0.29
     Vermont
    -0.29
     federally
    -0.28
     Neighborhood
    -0.28
    alach
    -0.28
    POSITIVE LOGITS
     tyres
    0.40
    èĩªåĬ¨é©¾é©¶
    0.35
    å¥Ķé©°
    0.33
     manoe
    0.33
     Ferrari
    0.33
     tyre
    0.32
    ä¸ĩè¾Ĩ
    0.32
    驾驶
    0.31
     Airbus
    0.30
    eworld
    0.30
    Activations Density 0.089%

    No Known Activations