© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 540
    Prev
    Next
    INDEX
    Explanations

    associated with

    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
    ä¼ŀ
    -0.24
     minds
    -0.24
    æĬķå½±
    -0.22
     authority
    -0.22
     mind
    -0.22
    tre
    -0.22
    mai
    -0.21
    èĵĿåĽ¾
    -0.21
    gor
    -0.21
    ¥
    -0.21
    POSITIVE LOGITS
     decreased
    0.35
     decrease
    0.31
     increased
    0.31
     successful
    0.31
    Successful
    0.28
    /an
    0.28
    IED
    0.28
    increase
    0.27
     favorable
    0.27
    successful
    0.27
    Activations Density 0.159%

    No Known Activations