© 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. 34
    Prev
    Next
    INDEX
    Explanations

    describe/state/stored/basis

    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
    并å°Ĩ
    -0.28
     ìŀĪê³ł
    -0.23
    æĪĸå¤ļ
    -0.23
    æĪĸèĢħåħ¶ä»ĸ
    -0.22
     Scheduled
    -0.22
    Scheduled
    -0.22
     &_
    -0.22
    并
    -0.22
    composition
    -0.22
    ä¸Ģåı£
    -0.21
    POSITIVE LOGITS
     alike
    0.28
    recht
    0.23
    clus
    0.23
    lek
    0.22
    ç¬ij
    0.22
    NONE
    0.21
    é¼ĵ
    0.21
    SED
    0.21
     cle
    0.21
    -hover
    0.21
    Activations Density 0.910%

    No Known Activations