© 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. 11465
    Prev
    Next
    INDEX
    Explanations

    the full license

    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
    ãģĬ
    -0.29
    ãģĤãģ£ãģŁ
    -0.28
    ãģĻãģ§ãģ«
    -0.24
    ãĤĤãģ£ãģ¨
    -0.24
    ãĤĤãģ®
    -0.24
    ãģĻãģIJ
    -0.24
    ãģĻãģIJãģ«
    -0.24
    ãģĤãĤĭ
    -0.21
    对äºİ
    -0.21
    ãģĬ話
    -0.21
    POSITIVE LOGITS
     sake
    0.60
     purposes
    0.53
    bidden
    0.38
    geries
    0.35
    -profit
    0.33
    æĿ¥è¯´
    0.32
    amt
    0.31
    æĿ¥è®²
    0.30
    çĶ¨æĪ·æıIJä¾Ľ
    0.29
     reasons
    0.28
    Activations Density 0.154%

    No Known Activations