© 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. 347
    Prev
    Next
    INDEX
    Explanations

    upcoming events and announcements

    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
    å½ĵæŶçļĦ
    -0.26
    rafted
    -0.25
    å½ĵæŶ
    -0.25
    æĹĹä¸ĭçļĦ
    -0.25
    otropic
    -0.24
    æľ¬èº«çļĦ
    -0.24
    ä¸İæŶ
    -0.23
    å¾Ĺä½ı
    -0.23
    æľ¬èº«
    -0.22
    åİŁæĿ¥
    -0.22
    POSITIVE LOGITS
     trends
    0.24
    æĪĸå°Ĩ
    0.23
     Soon
    0.23
    LY
    0.23
     soon
    0.22
    Soon
    0.21
     generations
    0.21
    åįģåĪĨéĩįè¦ģ
    0.21
     tense
    0.21
     revelations
    0.20
    Activations Density 0.007%

    No Known Activations