© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12335
    Prev
    Next
    INDEX
    Explanations

    parallel, randomized, controlled trial

    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
    Not in Any Lists

    No Comments

    Negative Logits
     san
    -0.23
    san
    -0.22
    speaker
    -0.19
    yo
    -0.19
    ATIC
    -0.19
    ãģ°ãģĭãĤĬ
    -0.18
    atos
    -0.18
     sane
    -0.18
    举æŃ¢
    -0.18
    finish
    -0.18
    POSITIVE LOGITS
    pread
    0.18
    Ñħи
    0.18
    åĪĨãģij
    0.18
    _nb
    0.18
    ith
    0.18
     обÑĥÑĩениÑı
    0.17
    (pts
    0.17
    Intl
    0.17
     Firewall
    0.17
    ä¸Ģåı°
    0.17
    Activations Density 0.024%

    No Known Activations