© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 233
    Prev
    Next
    INDEX
    Explanations

    Supreme Court, landmark, Review, World, cases

    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
     Cute
    -0.27
    æĹºåŃ£
    -0.26
     Atat
    -0.25
     %-
    -0.25
     economy
    -0.25
     vib
    -0.24
     suited
    -0.24
    IFI
    -0.23
    recur
    -0.23
     versatility
    -0.23
    POSITIVE LOGITS
    annon
    0.30
    ç¡®ç«ĭ
    0.28
     landmark
    0.28
    æµģ产
    0.27
    æĴ¤éĶĢ
    0.27
    æľĢç»Ī
    0.26
    宣åijĬ
    0.26
    举æĬ¥
    0.26
    æ¡Īä»¶
    0.26
     Announcement
    0.26
    Activations Density 0.024%

    No Known Activations