© 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. 13850
    Prev
    Next
    INDEX
    Explanations

    org.codehaus

    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
    busters
    -0.20
    orte
    -0.17
    olina
    -0.17
    ties
    -0.17
    rist
    -0.17
    emin
    -0.16
    ically
    -0.16
    ¹
    -0.16
    enate
    -0.15
    gest
    -0.15
    POSITIVE LOGITS
    ģ
    0.20
    ihu
    0.16
    æħĭ
    0.16
    каÑĢ
    0.15
    éħ¤
    0.15
    ths
    0.15
    çIJĨä¼ļ
    0.15
    abel
    0.14
    ife
    0.14
    人éĢī
    0.14
    Activations Density 0.430%

    No Known Activations