© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14926
    Prev
    Next
    INDEX
    Explanations

    ice cream parlours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    èĥĮ
    -0.20
    aid
    -0.20
     Suites
    -0.20
    æķ¦
    -0.20
    è´¢åĬ¡
    -0.19
    æĸ¯åŁº
    -0.19
     Household
    -0.18
     blink
    -0.18
     Commit
    -0.18
    å¥ĹæĪ¿
    -0.18
    POSITIVE LOGITS
    åĶ®åįĸ
    0.24
    éľ²å¤©
    0.21
     outdoor
    0.21
    è´©åįĸ
    0.20
    娱ä¹IJåľº
    0.20
    路边
    0.20
    æł¡å¤ĸ
    0.19
    åĨĴçĿĢ
    0.19
    ryo
    0.19
    å²ļ
    0.19
    Activations Density 0.011%

    No Known Activations