© 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. 2589
    Prev
    Next
    INDEX
    Explanations

    water, heat, stress, cracking

    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
    prepared
    -0.28
    紧缺
    -0.25
    åĪ½
    -0.24
    å¸Ĥåľºè§Ħ模
    -0.24
    Completion
    -0.24
    ç¨ĥ
    -0.24
    å¢ŀè¿Ľ
    -0.23
    âļ¬
    -0.23
    market
    -0.23
    å¥īçĮ®
    -0.23
    POSITIVE LOGITS
    ä¾µèļĢ
    0.36
    ç©¿è¿ĩ
    0.28
     exterior
    0.27
    è·¯å¾Ħ
    0.27
     infiltration
    0.26
     lateral
    0.26
    ä¾µ
    0.26
    侵害
    0.25
     ingress
    0.25
     unchecked
    0.25
    Activations Density 0.042%

    No Known Activations