© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3092
    Prev
    Next
    INDEX
    Explanations

    future goals

    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
    æĶ¾å¼ĥäºĨ
    -0.28
    ç»ĻäºĨæĪij
    -0.28
    è¿Ľè¡ĮäºĨ
    -0.27
    åĩłä¹İæīĢæľī
    -0.27
    éĢłæĪIJäºĨ
    -0.27
     ceased
    -0.26
    失åİ»äºĨ
    -0.26
     previously
    -0.25
    åıĹåĪ°äºĨ
    -0.25
    ãģªãģıãģªãģ£ãģŁ
    -0.25
    POSITIVE LOGITS
    å°½åı¯èĥ½
    0.39
     hopefully
    0.37
     preferably
    0.36
    æĹ©æĹ¥
    0.34
     someday
    0.34
    å±ĬæŶ
    0.33
    尽快
    0.32
    å°½æĹ©
    0.32
     tomorrow
    0.31
    Hopefully
    0.31
    Activations Density 0.031%

    No Known Activations