© 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. 990
    Prev
    Next
    INDEX
    Explanations

    alternatively or option

    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
    æ³Ľ
    -0.26
    åħħæĸ¥
    -0.25
    chron
    -0.25
    缸åħ³åĨħ容
    -0.23
    å²Ľå±¿
    -0.22
    graphs
    -0.22
     histó
    -0.22
    rafted
    -0.22
    åıĺäºĨ
    -0.22
    æŀĦæĪIJäºĨ
    -0.22
    POSITIVE LOGITS
     alternatively
    0.39
    éĢĶå¾Ħ
    0.38
    Alternatively
    0.38
     option
    0.37
     Alternatively
    0.36
    å¾Īæĸ¹ä¾¿
    0.36
    æĸ¹å¼ı
    0.35
    ä¹Łåı¯ä»¥
    0.35
    åı¯ä»¥çĽ´æİ¥
    0.34
    æĸ¹å¼ıè¿Ľè¡Į
    0.34
    Activations Density 0.117%

    No Known Activations