© 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
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 161
    Prev
    Next
    INDEX
    Explanations

    stop loss

    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
     cryptography
    -0.31
    骨æŀ¶
    -0.28
     Magic
    -0.26
    Catalog
    -0.26
     Catalog
    -0.26
     Crypt
    -0.25
    èĤīä½ĵ
    -0.24
    magic
    -0.24
    apyrus
    -0.24
     cryptographic
    -0.23
    POSITIVE LOGITS
    æŃ¢æįŁ
    0.40
     setups
    0.32
    çŃĸçķ¥
    0.28
    é£İæݧ
    0.28
    è¿Ľåľº
    0.28
     trades
    0.27
    æŀľæĸŃ
    0.27
    ä¿ĿæĬ¤åĮº
    0.27
     loss
    0.26
    é£İéĻ©ç®¡çIJĨ
    0.26
    Activations Density 0.016%

    No Known Activations