© 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. 1026
    Prev
    Next
    INDEX
    Explanations

    start 'npm'

    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
    _backward
    -0.26
    Grammar
    -0.22
    -forward
    -0.22
    æĿ¥ä¸įåıĬ
    -0.21
    (vc
    -0.21
    -sn
    -0.21
     helmets
    -0.21
    lö
    -0.20
    languages
    -0.20
     vets
    -0.20
    POSITIVE LOGITS
    ings
    0.25
     SPL
    0.21
     owner
    0.21
    主人
    0.20
    oun
    0.20
     TWO
    0.20
     Fasc
    0.20
     agricultural
    0.20
     associ
    0.20
    主ä½ĵ
    0.19
    Activations Density 0.211%

    No Known Activations