© 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. 2054
    Prev
    Next
    INDEX
    Explanations

    cities and locations

    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
    ä¿Ĺ
    -0.28
    eldom
    -0.25
    éĶ¥
    -0.25
    å®ķ
    -0.24
     unreliable
    -0.24
    èµĸ以
    -0.23
    zek
    -0.23
     distrust
    -0.23
    outs
    -0.22
    olec
    -0.22
    POSITIVE LOGITS
    å±ĬæŶ
    0.41
    åį³å°ĨåĪ°æĿ¥
    0.36
    ä»Ĭå¹´
    0.34
    å°Ĩäºİ
    0.33
    æĺİå¹´
    0.33
     upcoming
    0.32
    举è¡ĮçļĦ
    0.32
    åľ¨ä»Ĭå¹´
    0.30
    举åĬŀçļĦ
    0.30
     tomorrow
    0.29
    Activations Density 0.035%

    No Known Activations