© 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. 17272
    Prev
    Next
    INDEX
    Explanations

    teacher actions and roles

    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
    entifier
    -0.21
    itecture
    -0.17
    tree
    -0.17
    èĻij
    -0.16
    noc
    -0.16
    uge
    -0.16
    temp
    -0.16
    åĭĥåĭĥ
    -0.16
    -sectional
    -0.16
    sing
    -0.16
    POSITIVE LOGITS
    (s
    0.20
    们çļĦ
    0.19
    hood
    0.18
     воÑĤ
    0.18
    otle
    0.18
    preneur
    0.17
     вÑģего
    0.17
    atura
    0.16
    -than
    0.16
    SON
    0.16
    Activations Density 0.007%

    No Known Activations