© 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. 2614
    Prev
    Next
    INDEX
    Explanations

    Mount Rushmore, questions, public arguments

    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
    aya
    -0.27
    simple
    -0.24
    tractor
    -0.23
    pagen
    -0.23
    _ring
    -0.23
    ard
    -0.23
    xin
    -0.22
    _voltage
    -0.22
    ldata
    -0.22
    太éĺ³åŁİ
    -0.22
    POSITIVE LOGITS
    æĥħèĬĤ
    0.24
    æݨçIJĨ
    0.24
     jewellery
    0.23
    âĨ©
    0.22
    åīŀ
    0.22
    æŀļ
    0.22
    æµģåIJij
    0.22
     sil
    0.22
    è¹ģ
    0.22
    çŁ¾
    0.22
    Activations Density 0.002%

    No Known Activations