© 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. 14760
    Prev
    Next
    INDEX
    Explanations

    copyright or license notices

    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
    æŶéĹ´åĴĮ
    -0.19
     zwar
    -0.18
    ãģ¾ãģĻ
    -0.18
    管çIJĨåĴĮ
    -0.18
     zarówno
    -0.17
    oret
    -0.17
    è¿Ļæīį
    -0.17
    ä¸įä»ħè¦ģ
    -0.17
     meisten
    -0.16
    çļĦ好å¤Ħ
    -0.16
    POSITIVE LOGITS
    phans
    0.56
    thon
    0.46
    acles
    0.43
    ifice
    0.42
    ients
    0.35
    lando
    0.35
    naments
    0.34
    åħ¶å®ĥ
    0.34
    ific
    0.34
    acular
    0.33
    Activations Density 0.332%

    No Known Activations