© 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. 2415
    Prev
    Next
    INDEX
    Explanations

    sits in a location

    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
    metro
    -0.24
     пиÑĤаниÑı
    -0.22
    窮
    -0.22
     reconsider
    -0.21
    ysis
    -0.21
    åĪ°
    -0.21
    -material
    -0.21
    liness
    -0.21
    åĴĮçĿ¦
    -0.21
    ISTA
    -0.20
    POSITIVE LOGITS
     undefeated
    0.28
    ún
    0.26
    elve
    0.24
     Ñģобой
    0.24
    urd
    0.24
    enu
    0.23
    ä¿ĿæĮģçĿĢ
    0.23
    ares
    0.23
     nestled
    0.23
    深深çļĦ
    0.23
    Activations Density 0.031%

    No Known Activations