© 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. 2808
    Prev
    Next
    INDEX
    Explanations

    agreement/disagreement

    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
    椿
    -0.27
    âĢ¹
    -0.25
     Universal
    -0.24
     universal
    -0.24
    åīįå¾Ģ
    -0.23
    Universal
    -0.23
    å¾Ģ
    -0.23
    æŶéĹ´ä¸º
    -0.22
     Browse
    -0.22
    è§Ĵ
    -0.22
    POSITIVE LOGITS
    è¿ĻçĤ¹
    0.29
    è¿Ļç§įæĥħåĨµ
    0.28
    è¿Ļ个éĹ®é¢ĺ
    0.28
    çļĦç¡®
    0.27
     Nope
    0.27
    è¿Ļä¸ĢçĤ¹
    0.27
     disagree
    0.27
    確ãģĭãģ«
    0.27
     yes
    0.27
     indeed
    0.26
    Activations Density 0.047%

    No Known Activations