© 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. 1370
    Prev
    Next
    INDEX
    Explanations

    edge of court

    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
    decess
    -0.23
    賦
    -0.23
    uario
    -0.23
    addons
    -0.23
    ippy
    -0.22
    rist
    -0.22
     alphabetical
    -0.22
    纡
    -0.21
    .sources
    -0.21
     divers
    -0.21
    POSITIVE LOGITS
    ä¸ĢæĿ¡
    0.30
    两æĿ¡
    0.28
    宾é¦Ĩ
    0.27
    staff
    0.26
    缮æłĩä»»åĬ¡
    0.26
    缮æłĩ
    0.26
    è¾¹çķĮ
    0.25
    æłı
    0.25
    éĺ²çº¿
    0.25
    æĶ¶å®ĺ
    0.24
    Activations Density 0.002%

    No Known Activations