© 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. 841
    Prev
    Next
    INDEX
    Explanations

    as the name suggests

    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
    ç³ľ
    -0.23
    ko
    -0.23
    åIJ¸
    -0.22
    []{
    -0.21
    çļĦè§ĤçĤ¹
    -0.21
    _HP
    -0.21
    vell
    -0.21
    ç¹ĩ
    -0.20
     inc
    -0.20
    pras
    -0.20
    POSITIVE LOGITS
    cth
    0.25
    (^
    0.24
     intend
    0.24
    è¿Ļæĺ¯ä¸Ģ个
    0.23
    为人
    0.23
    åŃĸ
    0.23
    spy
    0.22
    è¡
    0.22
    »¿
    0.22
    ign
    0.22
    Activations Density 0.020%

    No Known Activations