© 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. 16479
    Prev
    Next
    INDEX
    Explanations

    send an email

    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
    aus
    -0.22
    åĹĵ
    -0.19
    eras
    -0.17
    è¯Ŀè¯ŃæĿĥ
    -0.17
    ansen
    -0.17
    arter
    -0.17
    hood
    -0.17
    è£Ļ
    -0.17
    sgi
    -0.16
    /ext
    -0.16
    POSITIVE LOGITS
    æĪijåİ»
    0.27
     forth
    0.23
    åĩºåİ»
    0.23
     Ø¥ÙĦÙĬÙĩ
    0.20
    iment
    0.20
    inel
    0.20
    ToFront
    0.19
    è¿ĩæĿ¥
    0.19
    มà¸Ńà¸ļ
    0.18
    ToList
    0.18
    Activations Density 0.083%

    No Known Activations