© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14433
    Prev
    Next
    INDEX
    Explanations

    numerical amounts

    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
    ðŁı»
    -0.20
    ject
    -0.19
    æĪĺåĽ½
    -0.18
    åģ¥åº·æĪIJéķ¿
    -0.18
    èį¤
    -0.17
    bed
    -0.17
    Ùĭ
    -0.17
    æ¦Ī
    -0.17
     Bout
    -0.17
    raising
    -0.17
    POSITIVE LOGITS
    sar
    0.20
    ielding
    0.20
    è¾Ľèĭ¦
    0.19
    .future
    0.18
     wÅĽ
    0.18
    å°±è¿Ļä¹Ī
    0.18
     uçu
    0.17
    ngen
    0.17
    ÑģÑħ
    0.17
    mah
    0.17
    Activations Density 0.013%

    No Known Activations