© 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. 719
    Prev
    Next
    INDEX
    Explanations

    with the x of

    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
    _asm
    -0.23
     вÑģÑĤÑĢеÑĩа
    -0.22
    Say
    -0.22
    æ¹į
    -0.21
    ENA
    -0.21
    Long
    -0.21
    ITY
    -0.21
    åĨįä¹Łä¸į
    -0.21
    æľīç§į
    -0.21
    holes
    -0.20
    POSITIVE LOGITS
    æħİéĩį
    0.25
    æīįåı¯ä»¥
    0.23
    æĪijæīį
    0.23
    çļĦ带é¢Ĩä¸ĭ
    0.23
    åıĮçľ¼
    0.23
    ç»ĻäºĨæĪij
    0.23
    æľĽåİ»
    0.22
    ç½²
    0.22
    ayload
    0.22
    ä»Ģä¹ĪåİŁåĽł
    0.22
    Activations Density 0.254%

    No Known Activations