© 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. 2838
    Prev
    Next
    INDEX
    Explanations

    list items in parentheses

    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
    人åĬĽ
    -0.24
    äºĨ好å¤ļ
    -0.24
    å¾Īæľī
    -0.23
    gie
    -0.23
     chances
    -0.22
     Fortune
    -0.22
    aven
    -0.22
     hopes
    -0.22
     Mystery
    -0.22
     ÑģкаÑĩ
    -0.21
    POSITIVE LOGITS
    (ii
    0.28
    ä½Ĩä¸įéĻIJäºİ
    0.27
     prelim
    0.26
    enumerate
    0.26
    èĹľ
    0.24
    _REGISTER
    0.23
     whichever
    0.23
    以åıĬåħ¶ä»ĸ
    0.22
    廳
    0.22
    ragments
    0.21
    Activations Density 0.050%

    No Known Activations