© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12181
    Prev
    Next
    INDEX
    Explanations

    wondering whether

    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
    -wow
    -0.26
     WOW
    -0.25
     helicopt
    -0.24
    wow
    -0.23
    çĬŁ
    -0.23
    _busy
    -0.22
     sodom
    -0.22
    çħ³
    -0.22
     libertin
    -0.21
     swingers
    -0.21
    POSITIVE LOGITS
    ãģ£ãģ¦ãĤĭ
    0.28
     gonna
    0.27
     fucking
    0.25
     kinda
    0.24
    åīŁ
    0.23
     wanna
    0.22
     absolute
    0.22
    á´¼
    0.22
    毫æĹł
    0.21
     half
    0.21
    Activations Density 0.563%

    No Known Activations