© 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. 1076
    Prev
    Next
    INDEX
    Explanations

    lone, solitary, surrounded

    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
     ties
    -0.26
    æĬ¥å¤į
    -0.25
    .rel
    -0.24
     tie
    -0.24
    itura
    -0.23
    天ä¸Ĭ
    -0.23
    enci
    -0.22
    èµĻ
    -0.22
     Kö
    -0.22
    reve
    -0.21
    POSITIVE LOGITS
    åѤåįķ
    0.44
     surrounded
    0.42
     lone
    0.41
    åѤ
    0.39
    åѤçĭ¬
    0.39
    åѤç«ĭ
    0.37
     hostile
    0.33
     solitary
    0.33
    åģĮ
    0.32
     surroundings
    0.32
    Activations Density 0.088%

    No Known Activations