© 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. 2994
    Prev
    Next
    INDEX
    Explanations

    operating systems and hardware

    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
    ervo
    -0.25
    oise
    -0.24
    ders
    -0.24
    ä¹ŁåIJĮæł·
    -0.23
    åĴĮ个人
    -0.23
    advertisement
    -0.22
    Earn
    -0.21
     зай
    -0.21
     protagon
    -0.21
    '.$
    -0.21
    POSITIVE LOGITS
     Basic
    0.28
     basic
    0.24
    åŁºæľ¬
    0.23
     Composite
    0.22
     Revision
    0.22
     Extension
    0.22
    EE
    0.22
    常çĶ¨
    0.22
     basics
    0.22
     plain
    0.22
    Activations Density 0.082%

    No Known Activations