© 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. 1907
    Prev
    Next
    INDEX
    Explanations

    Louisiana legal cases

    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
     лиÑĪÑĮ
    -0.26
    æĢľ
    -0.24
    èĻı
    -0.23
     lá»ĩnh
    -0.21
     legally
    -0.21
    lest
    -0.21
    /Linux
    -0.21
    linger
    -0.21
    location
    -0.21
    격
    -0.20
    POSITIVE LOGITS
    raries
    0.29
    NewLabel
    0.26
    itud
    0.25
    ngth
    0.25
    hores
    0.23
    RARY
    0.23
    shade
    0.23
    abeled
    0.23
    Ĵ
    0.22
    UNCH
    0.21
    Activations Density 1.838%

    No Known Activations