© 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. 2284
    Prev
    Next
    INDEX
    Explanations

    sun protection and skin care

    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
    Platform
    -0.22
    éĵģè·¯
    -0.22
    _wire
    -0.22
     Luo
    -0.22
     railway
    -0.21
    Wire
    -0.21
    西路
    -0.21
    èŁĭ
    -0.21
    mts
    -0.21
    Bag
    -0.21
    POSITIVE LOGITS
    éĺ²æĻĴ
    0.31
     sunscreen
    0.31
    å¤ıæĹ¥
    0.29
     lotion
    0.26
    æ¶ĤæĬ¹
    0.25
     allergy
    0.24
    æĬ¤èĤ¤
    0.24
     impact
    0.22
     Jungle
    0.22
    utely
    0.22
    Activations Density 0.004%

    No Known Activations