© 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. 17206
    Prev
    Next
    INDEX
    Explanations

    VGA, RPM, RCA, MSI, SC, kg

    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
    rix
    -0.17
    å£ķ
    -0.17
    ork
    -0.17
    _#{
    -0.17
    unge
    -0.17
    usz
    -0.16
    uality
    -0.16
    失ä¸ļ
    -0.16
    hid
    -0.16
    urb
    -0.16
    POSITIVE LOGITS
    esimal
    0.19
    aler
    0.18
    彩
    0.17
    纽带
    0.17
    çŃīä¸Ģæī¹
    0.17
    çĨŁ
    0.17
    ç°¿
    0.17
    è¡Ķæİ¥
    0.16
    ibrary
    0.16
    wright
    0.16
    Activations Density 0.008%

    No Known Activations