© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10411
    Prev
    Next
    INDEX
    Explanations

    status changes or lifecycle events

    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
    Negative Logits
    ABCDEFG
    -0.24
    CALLTYPE
    -0.22
    "urls
    -0.21
    PropertyParams
    -0.21
    VMLINUX
    -0.21
    chez
    -0.20
    itches
    -0.19
     dó
    -0.19
    ,eg
    -0.19
     hor
    -0.18
    POSITIVE LOGITS
     status
    0.28
    çĬ¶æĢģä¸ĭ
    0.28
    çĬ¶æĢģ
    0.26
     pending
    0.25
    Pending
    0.24
    æĢģ
    0.24
    çĭĢæħĭ
    0.23
    Active
    0.23
    Status
    0.23
     Pending
    0.22
    Activations Density 0.268%

    No Known Activations