© 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. 1916
    Prev
    Next
    INDEX
    Explanations

    Al-Qaeda, FBI, SpaceX, Hamilton

    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
    åIJĦç§įåIJĦæł·
    -0.24
    ä¸Ģä¸ĭåŃIJå°±
    -0.23
    borrow
    -0.23
    ä¹Łæľīå¾Īå¤ļ
    -0.23
    å®īä¸ľå°¼
    -0.23
    idl
    -0.22
    mtree
    -0.22
    è¿Ļ两ç§į
    -0.22
    pole
    -0.22
    æŀ¶åŃIJ
    -0.22
    POSITIVE LOGITS
    ç»Ŀ
    0.30
    æ¦Ĥ
    0.28
    å¿«
    0.28
     woes
    0.25
    åīį线
    0.24
     дело
    0.24
    ç»Ŀ对
    0.24
    åħ¶
    0.23
    æ²ī
    0.22
    å±ıéļľ
    0.22
    Activations Density 0.121%

    No Known Activations