© 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. 12713
    Prev
    Next
    INDEX
    Explanations

    computer hardware models

    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
    è·ĸ
    -0.20
     Huff
    -0.20
    eor
    -0.20
    uru
    -0.19
    brown
    -0.19
    ยะ
    -0.18
    æĿijåħļæĶ¯éĥ¨
    -0.18
    å®ħ
    -0.18
    orative
    -0.18
    etry
    -0.18
    POSITIVE LOGITS
     lin
    0.20
     Truck
    0.20
     pron
    0.20
    们
    0.19
    æĬĹéľĩ
    0.19
    é²²
    0.18
     pomp
    0.18
     Seah
    0.18
     fancy
    0.18
    redential
    0.17
    Activations Density 0.006%

    No Known Activations