© 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. 1501
    Prev
    Next
    INDEX
    Explanations

    more likely

    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
    maybe
    -0.24
    fulness
    -0.23
    çĦ¶æĺ¯
    -0.23
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.23
    ess
    -0.23
    perhaps
    -0.22
    -error
    -0.21
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    -0.21
    侯
    -0.21
    å¾Ĺå¾Ī
    -0.21
    POSITIVE LOGITS
    senal
    0.25
     interesting
    0.22
    AVIS
    0.21
     Detaylı
    0.21
    schlü
    0.21
    europäische
    0.21
    åħīæĺİ
    0.20
     Bookmark
    0.20
    æ¯ĶæĪij
    0.20
     capable
    0.20
    Activations Density 0.030%

    No Known Activations