© 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. 725
    Prev
    Next
    INDEX
    Explanations

    inauguration, inaugural, unveil(ed)

    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
    ily
    -0.23
    tem
    -0.22
    tems
    -0.21
     overhe
    -0.20
    å½Ĵ纳
    -0.19
    IBILITY
    -0.19
    çĭĹ
    -0.19
    åĽº
    -0.19
    dea
    -0.19
     onChanged
    -0.19
    POSITIVE LOGITS
    sla
    0.21
     Scotia
    0.21
    atory
    0.21
     ceremony
    0.21
     respective
    0.20
    çļĦç¬ij容
    0.20
     lá»Ļ
    0.19
    /down
    0.19
     Romney
    0.19
    iated
    0.19
    Activations Density 0.004%

    No Known Activations