© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1668
    Prev
    Next
    INDEX
    Explanations

    have any

    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»Ģä¹Īåij¢
    -0.24
     unequiv
    -0.24
    mando
    -0.23
    Poss
    -0.23
     undeniable
    -0.22
    ided
    -0.22
    å¾Ī大ç¨ĭ度
    -0.21
     probably
    -0.21
    erule
    -0.21
     Reeves
    -0.21
    POSITIVE LOGITS
    ä»»ä½ķ
    0.38
    æľīä»»ä½ķ
    0.38
     any
    0.34
     лÑİбого
    0.30
    åĨįå¤ļ
    0.29
    ä»»ä½ķä¸Ģ个
    0.28
    ä¸įæħİ
    0.28
    ä»»ä½ķå½¢å¼ı
    0.26
    éĹ²ç½®
    0.26
    any
    0.26
    Activations Density 0.022%

    No Known Activations