© 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. 865
    Prev
    Next
    INDEX
    Explanations

    age, aged, aging, years, older

    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
    çļĦç«ŀäºī
    -0.28
    çĨŁæĤī
    -0.26
    åĴ«
    -0.24
    á»Ļc
    -0.23
    çŁŃæļĤ
    -0.23
    /wait
    -0.23
     trainers
    -0.23
     ÑĢаÑģÑħод
    -0.23
    槽
    -0.23
    åIJ¸å¼ķ
    -0.23
    POSITIVE LOGITS
    å²ģ以ä¸Ĭ
    0.40
     age
    0.40
    å¹´é¾Ħ
    0.39
    -aged
    0.39
     aged
    0.39
    -age
    0.38
     aging
    0.37
    å¹´é¾Ħ段
    0.37
     ages
    0.37
    èĢģ年人
    0.37
    Activations Density 0.151%

    No Known Activations