© 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. 1545
    Prev
    Next
    INDEX
    Explanations

    magazine and journal titles

    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
    çĦī
    -0.26
    NavController
    -0.24
    unicip
    -0.24
    PostBack
    -0.23
    æĥ³èµ·äºĨ
    -0.23
    .setOutput
    -0.23
     Mare
    -0.22
    æłijæŀĿ
    -0.22
    建æĪIJåIJİ
    -0.22
    Github
    -0.22
    POSITIVE LOGITS
     magazine
    0.79
    æĿĤå¿Ĺ
    0.70
     magazines
    0.66
     Magazine
    0.66
    æĿĤå¿Ĺ社
    0.54
    æľŁåĪĬ
    0.44
    åĪĬçī©
    0.44
     ÙħجÙĦØ©
    0.40
    åij¨åĪĬ
    0.40
     journal
    0.39
    Activations Density 0.076%

    No Known Activations