© 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. 2408
    Prev
    Next
    INDEX
    Explanations

    aggregate data or collection

    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
    fulness
    -0.24
    aces
    -0.22
    ning
    -0.21
     utmost
    -0.21
    outs
    -0.21
     latter
    -0.20
    onet
    -0.20
    积æŀģéħįåIJĪ
    -0.20
    icion
    -0.20
    鼷æĸ¯
    -0.20
    POSITIVE LOGITS
     kê
    0.22
     liability
    0.21
    ption
    0.21
    åĴĮ个人
    0.20
    ByKey
    0.20
     revenues
    0.19
    OrNull
    0.19
    æīĭä¸ĭ
    0.19
    æĶ¶æ¬¾
    0.19
    /com
    0.19
    Activations Density 0.018%

    No Known Activations