© 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. 14210
    Prev
    Next
    INDEX
    Explanations

    it is time for

    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
    ä¸ĢæŶ
    -0.21
    ç»ĪçĶŁ
    -0.20
    åħµé©¬
    -0.20
    åIJ¬èµ·æĿ¥
    -0.20
    并ä¸įèĥ½
    -0.19
    汧
    -0.19
    åıªè¦ģæľī
    -0.19
    è´¸
    -0.19
    è¿Ń
    -0.19
    æĢķ
    -0.19
    POSITIVE LOGITS
    cé
    0.22
    owel
    0.20
    æĭIJ
    0.19
    s
    0.19
    asant
    0.19
    å·²ä¹ħ
    0.18
    è¡Įæĥħ
    0.18
    oden
    0.18
     overdue
    0.18
    以æĿ¥
    0.17
    Activations Density 0.011%

    No Known Activations