© 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. 1311
    Prev
    Next
    INDEX
    Explanations

    resemblance or similarity

    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
     lint
    -0.23
    å±ģ
    -0.23
     informat
    -0.23
    _TXT
    -0.22
     treats
    -0.22
    §è¡Į
    -0.22
     redund
    -0.22
    æĸĻ
    -0.22
    erta
    -0.21
    è§ĦèĮĥåĮĸ
    -0.21
    POSITIVE LOGITS
    çļĦæ¨¡æł·
    0.35
    容è²Į
    0.34
     resemblance
    0.33
     identity
    0.29
     likeness
    0.29
    身æĿIJ
    0.29
    æ¨¡æł·
    0.28
     facial
    0.28
     ident
    0.28
     morph
    0.28
    Activations Density 0.041%

    No Known Activations