© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 402
    Prev
    Next
    INDEX
    Explanations

    second occurrences or related words

    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
    ä¸ĢæŃ¥æŃ¥
    -0.22
    Delegate
    -0.22
    åѤç«ĭ
    -0.22
    ä¸ĢåĽ¢
    -0.21
    个åĪ«
    -0.21
    ĥģ
    -0.21
    spiracy
    -0.21
    缮åīį为æŃ¢
    -0.21
     Cave
    -0.21
    å¿ĥå¾Ĺ
    -0.21
    POSITIVE LOGITS
    -than
    0.27
    /rec
    0.25
    绿水
    0.25
    è¾īçħĮ
    0.25
    -life
    0.23
    (second
    0.23
    æĪĸå¤ļ
    0.23
     parad
    0.23
    osa
    0.23
    SECOND
    0.22
    Activations Density 0.028%

    No Known Activations