© 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. 14077
    Prev
    Next
    INDEX
    Explanations

    EFF, Terrence, and Peta

    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
     Clayton
    -0.20
    æĹıèĩªæ²»
    -0.19
    æĨ©
    -0.18
    éĻIJãĤĬ
    -0.18
    -mf
    -0.18
    xEE
    -0.18
    setQuery
    -0.18
    esModule
    -0.18
     getField
    -0.17
    并ä¸įæĦıåij³
    -0.17
    POSITIVE LOGITS
    æ±ī
    0.20
    æĢ»éĥ¨
    0.20
    宣
    0.19
    åĻ»
    0.19
    bett
    0.19
    æľ¬æĿ¥å°±
    0.19
    ÃŁen
    0.18
    èį¯çī©
    0.18
    ogan
    0.18
    apia
    0.18
    Activations Density 0.001%

    No Known Activations