© 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. 2421
    Prev
    Next
    INDEX
    Explanations

    founder or partner roles

    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
    Exercise
    -0.24
    Keyword
    -0.24
     volte
    -0.23
     Exercise
    -0.23
     SEL
    -0.23
    agree
    -0.23
    orate
    -0.22
    IZE
    -0.22
    exercise
    -0.22
     exercise
    -0.22
    POSITIVE LOGITS
    ç»ĦæĪIJ
    0.30
     contributing
    0.30
     composing
    0.29
    ç»ĦæĪIJçļĦ
    0.28
    åħ±åIJĮ
    0.28
    åĪ°æľĢåIJİ
    0.26
    ä¹ĭä¸Ģ
    0.26
    æŀĦæĪIJ
    0.25
     alongside
    0.24
    ç»Ħ
    0.23
    Activations Density 0.108%

    No Known Activations