© 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. 14127
    Prev
    Next
    INDEX
    Explanations

    child development or psychology

    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
    lev
    -0.20
    ikt
    -0.19
    å¾ķ
    -0.19
    两åįĥ
    -0.19
    TypeInfo
    -0.19
    å°ijçĪ·
    -0.19
     Fuck
    -0.19
    åijĬè¯īä½ł
    -0.18
    ron
    -0.18
    prot
    -0.18
    POSITIVE LOGITS
    对åŃ©åŃIJ
    0.54
    ç»ĻåŃ©åŃIJ
    0.50
    åŃ©åŃIJ
    0.46
    åŃ©åŃIJçļĦ
    0.43
    让åŃ©åŃIJ
    0.43
    åŃ©åŃIJ们
    0.41
    èĤ²åĦ¿
    0.40
     children
    0.35
    家éķ¿
    0.34
     child
    0.33
    Activations Density 0.129%

    No Known Activations