© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12413
    Prev
    Next
    INDEX
    Explanations

    programming and technology

    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
    æĸĩä½ĵ
    -0.25
    anto
    -0.22
    dy
    -0.20
    çĦ¶æĺ¯
    -0.20
    åŀĴ
    -0.19
    é«ĺçļĦ
    -0.19
    åºļ
    -0.18
    elen
    -0.18
    iler
    -0.18
    .libs
    -0.18
    POSITIVE LOGITS
     вообÑīе
    0.23
    çĪ±å¥½èĢħ
    0.20
    åħ¶å®ĥéĹ®é¢ĺ
    0.20
    家åĬ¡
    0.19
    _lifetime
    0.19
    èĦĺ
    0.19
    è¿Ļ件äºĭæĥħ
    0.19
    é¢Ĭ
    0.18
    è¿Ļ件äºĭ
    0.18
     überhaupt
    0.18
    Activations Density 0.398%

    No Known Activations