© 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. 890
    Prev
    Next
    INDEX
    Explanations

    micro four thirds camera, rxjs, code identifiers

    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
    dÃŃ
    -0.29
    pNext
    -0.23
    æĨ§
    -0.22
    ÑijÑĢ
    -0.22
    åįģä½³
    -0.21
     Curtain
    -0.21
    å¿ĥä¸ŃçļĦ
    -0.21
     дÑĢев
    -0.20
    ç¬ı
    -0.20
    æľªæĿ¥åıijå±ķ
    -0.20
    POSITIVE LOGITS
    he
    0.24
     investig
    0.24
    Ze
    0.23
    对åºĶ
    0.23
     Investig
    0.23
    alice
    0.22
    æ¹ĸ
    0.22
     UserModel
    0.22
    navigator
    0.22
    åıĤ
    0.22
    Activations Density 0.001%

    No Known Activations