© 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. 13696
    Prev
    Next
    INDEX
    Explanations

    access to resources

    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
    纤
    -0.21
    avic
    -0.20
    displayName
    -0.18
    åİ»åĵªåĦ¿
    -0.18
    èħ¹
    -0.18
    åįİåĮĹ
    -0.17
     ÐĵоÑĢ
    -0.17
    .serialization
    -0.17
    æ¬
    -0.17
    quares
    -0.17
    POSITIVE LOGITS
     access
    0.32
    (access
    0.28
    æĿĥéĻIJ
    0.27
    access
    0.25
    ãĤ¢ãĤ¯ãĤ»ãĤ¹
    0.25
     acesso
    0.24
     лиÑĨ
    0.24
    _ACCESS
    0.23
    Denied
    0.23
    _DENIED
    0.22
    Activations Density 0.062%

    No Known Activations