© 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. 2323
    Prev
    Next
    INDEX
    Explanations

    years or age ranges

    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
     amongst
    -0.38
    Whilst
    -0.36
     whilst
    -0.33
     Whilst
    -0.33
    æħ¢æħ¢çļĦ
    -0.33
    ä¸įåģľçļĦ
    -0.32
    åħ¶å®ĥ
    -0.32
    ä¸įæĸŃçļĦ
    -0.30
    éĥ¨ä»½
    -0.28
    éĿŀ常çļĦ
    -0.27
    POSITIVE LOGITS
    ä¸ĢçĤ¹åĦ¿
    0.32
    )—
    0.30
    —all
    0.29
    —↵↵
    0.29
    —but
    0.28
    —"
    0.28
    —including
    0.28
    —that
    0.27
    —not
    0.27
    "—
    0.26
    Activations Density 2.087%

    No Known Activations