© 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. 1840
    Prev
    Next
    INDEX
    Explanations

    state of being or perceived quality

    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
    åIJĦ个çݯèĬĤ
    -0.26
    //--
    -0.25
    主è¦ģåĮħæĭ¬
    -0.24
    æµģåIJij
    -0.24
    ellers
    -0.23
    ä¸Ģèµ·åİ»
    -0.23
    moving
    -0.23
    ijľ
    -0.22
    Åijs
    -0.22
    oose
    -0.22
    POSITIVE LOGITS
     heritage
    0.35
    ä¸İåIJ¦
    0.32
    çŁ¥åIJį度
    0.30
    åIJįæ°Ķ
    0.28
    inity
    0.27
     perceived
    0.26
    çī¹è´¨
    0.25
    çļĦç¼ĺæķħ
    0.25
    enuity
    0.25
    ä¸İä¼Ĺ
    0.25
    Activations Density 0.089%

    No Known Activations