© 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. 16511
    Prev
    Next
    INDEX
    Explanations

    power and utilities

    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
    maal
    -0.23
    æ¼Ĥæµģ
    -0.22
    é©»
    -0.19
    ammers
    -0.19
    çĥŃ度
    -0.19
    oint
    -0.19
    extr
    -0.19
    æľºåĻ¨
    -0.19
    çıŃ级
    -0.19
    VEN
    -0.18
    POSITIVE LOGITS
    çĶµåĬĽ
    0.33
    åıijçĶµ
    0.32
     electricity
    0.32
    çĶµç½ij
    0.29
    çĶµæ°Ķ
    0.28
     electric
    0.28
    electric
    0.26
    èĥ½æºIJ
    0.26
    çĶµä»·
    0.26
    éħįçĶµ
    0.26
    Activations Density 0.062%

    No Known Activations