© 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. 134
    Prev
    Next
    INDEX
    Explanations

    Material, Experience, Quantity, Texture

    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
    ãģ§ãģĻãģĹ
    -0.28
    aghan
    -0.27
    chers
    -0.25
    åħļåĴĮ
    -0.23
    .scalar
    -0.23
    -leg
    -0.22
     nik
    -0.22
    æĸĩåĮĸåĴĮ
    -0.21
     ?",
    -0.21
    acht
    -0.21
    POSITIVE LOGITS
    çijķ
    0.24
    çŃīçī¹çĤ¹
    0.23
    Ap
    0.22
    stamp
    0.22
    èģĶç³»çĶµè¯Ŀ
    0.21
    RE
    0.21
     origin
    0.21
     Ava
    0.21
    éĢĹ
    0.21
    大åŀĭ
    0.21
    Activations Density 0.237%

    No Known Activations