© 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. 11110
    Prev
    Next
    INDEX
    Explanations

    WhatsApp messaging app

    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
    ewidth
    -0.20
    AVIS
    -0.19
    /gpl
    -0.19
    ิà¸ĩ
    -0.19
     griev
    -0.18
    饯
    -0.18
    senal
    -0.18
    esub
    -0.17
    emouth
    -0.17
    asin
    -0.17
    POSITIVE LOGITS
    åıĺåĮĸ
    0.22
    çŀ³
    0.21
     patterns
    0.20
     Rodney
    0.19
    URN
    0.19
    ine
    0.18
    hol
    0.18
     puss
    0.18
     changes
    0.18
    çŃĴ
    0.18
    Activations Density 0.002%

    No Known Activations