© 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. 2310
    Prev
    Next
    INDEX
    Explanations

    Introduction marker {#s0005}

    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
    =nil
    -0.31
     Brigham
    -0.28
    FOUNDATION
    -0.25
     caliber
    -0.24
    çī¹æľĹ
    -0.24
     Tantra
    -0.23
    åİĿ
    -0.23
     tÃł
    -0.23
     Chattanooga
    -0.23
     Baylor
    -0.23
    POSITIVE LOGITS
     Catalonia
    0.29
     Leonardo
    0.28
    åįĩ温
    0.28
     Renault
    0.27
     Catalan
    0.26
     Sevilla
    0.26
     EURO
    0.26
     Euro
    0.26
     Parking
    0.25
     Spain
    0.25
    Activations Density 0.058%

    No Known Activations