© 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. 2577
    Prev
    Next
    INDEX
    Explanations

    buildings and places

    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
    @student
    -0.23
    iances
    -0.23
    å¾¼
    -0.23
    使çĶ¨èĢħæĪĸ
    -0.22
    ToList
    -0.22
    æĹ¥å¸¸å·¥ä½ľ
    -0.22
    ukkit
    -0.22
    缸åħ³è§Ħå®ļ
    -0.21
    çĻ½çĻ½
    -0.21
    æĻ¨æĬ¥
    -0.21
    POSITIVE LOGITS
    大楼
    0.35
     center
    0.34
    ä¹ĭ家
    0.33
    ä¸Ńå¿ĥ
    0.31
    å¹¿åľº
    0.30
     space
    0.29
    楼
    0.29
     Plaza
    0.29
     Center
    0.29
     headquarters
    0.28
    Activations Density 0.142%

    No Known Activations