© 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. 2591
    Prev
    Next
    INDEX
    Explanations

    emotional ride for me

    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
    æĪĸèĢħåħ¶ä»ĸ
    -0.28
    æĪĸåħ¶ä»ĸ
    -0.26
    ces
    -0.25
    quer
    -0.24
    æĪĸèĢħ
    -0.24
    ständ
    -0.23
    åįıåIJĮ
    -0.23
    ç»ıéªĮåĴĮ
    -0.22
    åĵ²
    -0.22
    çļĦç§ĺå¯Ĩ
    -0.22
    POSITIVE LOGITS
     commissioner
    0.26
     ìĿ´ë²Ī
    0.23
    æŃ¤æ¬¡
    0.23
     reordered
    0.23
    æѤæ¡Ī
    0.22
     Commissioner
    0.22
    åī¯å±Ģéķ¿
    0.21
    elog
    0.21
    éĢĻ次
    0.21
    è¿Ļ次
    0.21
    Activations Density 0.040%

    No Known Activations