© 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. 2501
    Prev
    Next
    INDEX
    Explanations

    fair use and copyright

    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
    manship
    -0.28
    .github
    -0.24
    Concurrency
    -0.23
    ÑģоÑģ
    -0.23
    éĦĻ
    -0.23
    timezone
    -0.23
    oco
    -0.23
    è´Ŀå°Ķ
    -0.23
    åIJĮåŁİ
    -0.23
     Installed
    -0.22
    POSITIVE LOGITS
    åħ¨æĸĩ
    0.30
    å¤įåį°
    0.28
    çīĩ段
    0.28
    éĥ¨åĪĨåĨħ容
    0.28
    èijĹä½ľæĿĥ
    0.28
    æĿĥåĪ©
    0.27
    è¾ij
    0.27
    åĩºçīĪ
    0.26
     infringement
    0.26
     copying
    0.26
    Activations Density 0.015%

    No Known Activations