© 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. 2559
    Prev
    Next
    INDEX
    Explanations

    children and age groups

    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
    æĿĥå¨ģ
    -0.26
    åħ¨åľº
    -0.23
    NEL
    -0.23
    失信
    -0.23
    ingen
    -0.22
    олÑĮ
    -0.22
    hed
    -0.22
    edi
    -0.22
    ç«ĭåľº
    -0.22
    ensa
    -0.21
    POSITIVE LOGITS
    éĺ¶æ®µ
    0.32
    odom
    0.27
    éĻªä½ł
    0.27
     phases
    0.27
    _inf
    0.26
     ages
    0.25
    èĮģ
    0.25
    åŃ£èĬĤ
    0.24
    éĢIJæ¸IJ
    0.24
    æ¸IJæ¸IJ
    0.24
    Activations Density 0.029%

    No Known Activations