© 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. 1470
    Prev
    Next
    INDEX
    Explanations

    sore throat

    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
    åĴĮåľ°åĮº
    -0.24
    ä¸¥æł¼
    -0.22
     اÙĦعربÙĬ
    -0.20
    rtl
    -0.20
    éro
    -0.20
    é¡·
    -0.18
    大èĩ´
    -0.18
    cir
    -0.18
    _DER
    -0.18
    ä¸Ĭè¿°
    -0.18
    POSITIVE LOGITS
    ness
    0.39
    NESS
    0.30
    ingly
    0.29
    ly
    0.28
    liest
    0.27
    ful
    0.25
    liness
    0.25
    lier
    0.25
    xes
    0.25
     جدا
    0.24
    Activations Density 0.001%

    No Known Activations