© 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. 1472
    Prev
    Next
    INDEX
    Explanations

    Saint Petersburg, Street, Jennifer

    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
    è´Ŀ壳
    -0.25
    å°ıé¾Ļ
    -0.25
     Nh
    -0.25
    owment
    -0.25
    aupt
    -0.24
    个ä½ĵ
    -0.23
    lict
    -0.23
    aml
    -0.22
    hoe
    -0.22
    udent
    -0.22
    POSITIVE LOGITS
    è¿¢
    0.26
     reflections
    0.25
     cr
    0.24
    å¼ķæĿ¥
    0.24
     sit
    0.23
     Stories
    0.23
    é£İæĥħ
    0.23
    äºĭ件
    0.23
     imaginary
    0.23
     dis
    0.23
    Activations Density 0.060%

    No Known Activations