© 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. 1722
    Prev
    Next
    INDEX
    Explanations

    take place

    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
     toss
    -0.22
    ovable
    -0.20
    hev
    -0.20
    ---</
    -0.20
    _mt
    -0.20
    éĩĮéĿ¢æľī
    -0.20
    ----</
    -0.20
    /flutter
    -0.20
    ä¸į满æĦı
    -0.19
     Hast
    -0.19
    POSITIVE LOGITS
     us
    0.25
    å¼ı
    0.24
    rise
    0.23
    缸å½ĵ
    0.23
    åĪ°æĿ¥
    0.23
    mo
    0.22
    å½¢å¼ı
    0.22
    çļĦæŶéĹ´
    0.22
    æŃ£
    0.22
    ÑģÑı
    0.21
    Activations Density 0.053%

    No Known Activations