© 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. 15964
    Prev
    Next
    INDEX
    Explanations

    systems design and development

    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
    é£Ķ
    -0.27
    èĸªèµĦ
    -0.26
    å½ĵ天
    -0.25
    åŁ¯
    -0.25
    çİĵ
    -0.25
    æĪij个人
    -0.25
    èİĻ
    -0.25
    ä¸Ģ个å°ı
    -0.25
    ä¾ĭåŃIJ
    -0.25
    åªĸ
    -0.25
    POSITIVE LOGITS
     relevant
    0.28
    ðŁĺĽ
    0.27
     Busty
    0.26
     dequeueReusableCellWithIdentifier
    0.25
    ðŁĺ¦
    0.25
     @"";↵
    0.25
     increasingly
    0.25
    ðŁ¤¦
    0.24
    èįł
    0.24
    æĢ¦
    0.24
    Activations Density 0.612%

    No Known Activations