© 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. 2542
    Prev
    Next
    INDEX
    Explanations

    chemical structures, programming terms, scientific contexts

    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
    å¼Ģå±Ģ
    -0.27
    edition
    -0.25
     renown
    -0.24
     âĿ¤
    -0.21
     payday
    -0.21
    社ä¼ļèµĦæľ¬
    -0.21
     bbw
    -0.21
     bookstore
    -0.21
     Hunters
    -0.20
    çĩĥæ²¹
    -0.20
    POSITIVE LOGITS
    ous
    0.24
    æĻ´
    0.23
    æĨ©
    0.23
    èĭĽ
    0.22
    éĢĹ
    0.22
     Gov
    0.22
    èĩªçIJĨ
    0.22
    Stub
    0.22
    BY
    0.22
    èĢ·
    0.22
    Activations Density 0.001%

    No Known Activations