© 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. 2456
    Prev
    Next
    INDEX
    Explanations

    low cost inexpensive cheap

    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
    豪
    -0.22
    æ³¾
    -0.22
    å¤±æľĽ
    -0.22
    æĹłç¼ĺ
    -0.22
     redeemed
    -0.22
     twice
    -0.21
    LOOP
    -0.21
     incorrectly
    -0.21
     streak
    -0.21
    éĿ¢å®¹
    -0.21
    POSITIVE LOGITS
    ä½İæĪIJæľ¬
    0.33
    æĪIJæľ¬
    0.31
     cost
    0.30
     inexpensive
    0.29
    åı¯è¡Į
    0.29
     resources
    0.28
    ä¸įé«ĺ
    0.28
    èµĦæºIJ
    0.28
    -scalable
    0.27
    ç®ĢåįķçļĦ
    0.27
    Activations Density 0.086%

    No Known Activations