© 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. 17056
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
    çĻ¾å¹´
    -0.21
     Walton
    -0.19
     sur
    -0.19
    UIT
    -0.19
     carp
    -0.19
     person
    -0.18
    ãĤīãģĦ
    -0.18
     Grinding
    -0.18
     bun
    -0.17
     Carpenter
    -0.17
    POSITIVE LOGITS
    ascal
    0.21
    _SCHEDULE
    0.19
    .asc
    0.19
    çģ¯çģ«
    0.18
    _hw
    0.18
    æ©IJ
    0.18
    odega
    0.18
    çĥŃ度
    0.18
    寡
    0.18
    /views
    0.18
    Activations Density 0.062%

    No Known Activations