© 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. 17168
    Prev
    Next
    INDEX
    Explanations

    Kim and names like Kim Stone, Kim Kaplan, Kim Harris

    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
    rieve
    -0.21
    ché
    -0.19
    ors
    -0.18
    junction
    -0.17
     gros
    -0.17
    ½æķ°
    -0.17
    ives
    -0.17
    ebin
    -0.17
    eur
    -0.17
    rees
    -0.15
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.18
    çĥŁèĬ±
    0.16
    ery
    0.15
    soever
    0.15
    ish
    0.15
    ights
    0.15
    å·ŀå¸Ĥ
    0.15
    etric
    0.15
    ï¸ı
    0.15
    èle
    0.14
    Activations Density 0.007%

    No Known Activations