© 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. 2586
    Prev
    Next
    INDEX
    Explanations

    type or style followed by descriptor

    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
    åĮĸè¿Ľç¨ĭ
    -0.26
    éĹ°
    -0.23
    icorn
    -0.22
    itel
    -0.22
    çĬŁ
    -0.22
     weir
    -0.21
    itian
    -0.21
    ophobia
    -0.20
    ibile
    -0.20
    æĺ¯éĿŀ
    -0.20
    POSITIVE LOGITS
    éĤ£æł·çļĦ
    0.28
    æł·çļĦ
    0.28
     обÑĢазом
    0.26
    åģı
    0.26
    ä¼¼çļĦ
    0.26
    ä¹ĭç±»çļĦ
    0.25
    ä¹ĭç±»
    0.25
    -wise
    0.25
    -like
    0.25
    类似
    0.24
    Activations Density 0.055%

    No Known Activations