© 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. 2225
    Prev
    Next
    INDEX
    Explanations

    Immunology, molecules, sports, journals

    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
    asured
    -0.23
    两项
    -0.23
    templ
    -0.23
    OPS
    -0.23
    APON
    -0.22
    æ§Ń
    -0.22
    åĩ«
    -0.22
    cycl
    -0.21
    ModuleName
    -0.21
    æįĤ
    -0.21
    POSITIVE LOGITS
    oad
    0.25
    çļĦè·Ŀ离
    0.25
     orders
    0.22
    ä¸ĬçļĦ
    0.22
     Shar
    0.22
    ä¸ĵ
    0.22
    ç¿ĺ
    0.21
    ocate
    0.21
     selectable
    0.21
    olate
    0.21
    Activations Density 0.030%

    No Known Activations