© 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. 16218
    Prev
    Next
    INDEX
    Explanations

    previously unpublished exclusive content

    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
    åĪ©åĻ¨
    -0.20
    åįĥ亿
    -0.19
    ä¸Ģç§į
    -0.19
    æĭ±
    -0.19
    ä¸įèī¯
    -0.18
    为æĬĵ
    -0.18
    .gov
    -0.18
    èĴ¯
    -0.18
    WithValue
    -0.18
    夹
    -0.18
    POSITIVE LOGITS
     interview
    0.20
     exclusively
    0.20
    çĭ¬å®¶
    0.19
    mas
    0.19
     Previously
    0.19
    é¦ĸ次
    0.19
    izio
    0.18
    ä»İæľª
    0.18
    Previously
    0.18
    æİĪæĿĥ
    0.18
    Activations Density 0.058%

    No Known Activations