© 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. 935
    Prev
    Next
    INDEX
    Explanations

    age requirements

    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
    UpdateTime
    -0.25
    ä¸ĩåħ¬éĩĮ
    -0.25
    PERT
    -0.24
    åIJĿ
    -0.23
    åIJĦæł·
    -0.22
    åIJĦç§įåIJĦæł·
    -0.22
     limp
    -0.22
    åŃļ
    -0.22
     ded
    -0.22
    ¹Ħ
    -0.22
    POSITIVE LOGITS
    æľªæĪIJ年人
    0.44
    å¹´é¾Ħ段
    0.43
    åĦ¿ç«¥
    0.42
    æľªæĪIJå¹´
    0.41
    å¹´é¾Ħ
    0.40
     age
    0.37
    -age
    0.37
    ç«¥
    0.35
    .age
    0.34
    éĿĴå°ijå¹´
    0.34
    Activations Density 0.007%

    No Known Activations