© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 692
    Prev
    Next
    INDEX
    Explanations

    NYT bestselling books and authors

    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
    ett
    -0.22
     liner
    -0.21
     serious
    -0.21
    æľįåĬ¡è´¨éĩı
    -0.20
     freely
    -0.20
    ampa
    -0.20
     specialised
    -0.20
     Ñģоб
    -0.19
     potentially
    -0.19
     specialized
    -0.19
    POSITIVE LOGITS
    ç§ĺè¯Ģ
    0.23
    /fast
    0.23
    ·¨
    0.22
    iler
    0.22
    绩
    0.21
    ãģĭãģ¤
    0.20
    eeee
    0.20
    éĶı
    0.20
    è¿Ļæł·è¯´
    0.20
    olves
    0.20
    Activations Density 0.003%

    No Known Activations