© 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. 14036
    Prev
    Next
    INDEX
    Explanations

    hyperactivity and activity

    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
    stellung
    -0.22
    stell
    -0.21
    akin
    -0.20
     depths
    -0.19
    飵åij³
    -0.19
    åĮł
    -0.19
    èıĺ
    -0.18
    åģľ
    -0.18
    篡
    -0.18
    裹
    -0.18
    POSITIVE LOGITS
    æ´»åĬ¨
    0.31
    æ´»è·ĥ
    0.30
    æ´»åĬĽ
    0.29
     Activity
    0.29
    /activity
    0.29
     activity
    0.28
    ç²¾åĬĽ
    0.26
    æ´»åĭķ
    0.26
    activity
    0.25
    活泼
    0.25
    Activations Density 0.023%

    No Known Activations