© 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. 941
    Prev
    Next
    INDEX
    Explanations

    disc words

    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
    ãģĹãģ¾ãģĨ
    -0.28
    wards
    -0.25
    -0.23
    ward
    -0.23
    ish
    -0.20
    ishly
    -0.20
    æĸ¯é¡¿
    -0.19
    WARDS
    -0.19
    ï¸ı
    -0.18
     mắn
    -0.18
    POSITIVE LOGITS
    ible
    0.23
    мен
    0.22
    ief
    0.20
    ãģĵãģ¨
    0.20
    rypto
    0.19
    ย
    0.19
    en
    0.19
    om
    0.18
    olor
    0.18
    ute
    0.17
    Activations Density 0.022%

    No Known Activations