© 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. 299
    Prev
    Next
    INDEX
    Explanations

    political parties and committees

    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
    elves
    -0.28
    ä¸Ģè§Ī
    -0.25
     measurable
    -0.24
    æİ¢éĻ©
    -0.24
    urance
    -0.23
    Cube
    -0.23
    ography
    -0.23
    ä¸Ģè¾ĪåŃIJ
    -0.23
     Cube
    -0.23
    æīĺç¦ı
    -0.23
    POSITIVE LOGITS
    åħļåĨħ
    0.39
    æī§æĶ¿
    0.34
    æ´¾
    0.34
    éĺµèIJ¥
    0.33
     faction
    0.32
     bloc
    0.32
     political
    0.32
    political
    0.31
    æĶ¿æ²»
    0.31
     party
    0.31
    Activations Density 0.046%

    No Known Activations