© 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. 11307
    Prev
    Next
    INDEX
    Explanations

    more detail or elaboration

    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
    ADER
    -0.21
    tons
    -0.20
    abra
    -0.20
    TON
    -0.20
    å®ī举
    -0.19
    leton
    -0.18
    UGHT
    -0.18
    æĹłè®ºå¦Ĥä½ķ
    -0.18
    åıįä¹ĭ
    -0.18
    常è¯Ĩ
    -0.18
    POSITIVE LOGITS
    ç»ĨèĬĤ
    0.34
     detail
    0.32
     details
    0.30
    ç»ĨåĮĸ
    0.26
     detalle
    0.26
    detail
    0.26
     detal
    0.25
     elabor
    0.25
     détail
    0.24
    (detail
    0.24
    Activations Density 0.059%

    No Known Activations