© 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. 13402
    Prev
    Next
    INDEX
    Explanations

    level image index cell

    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
    åıijçĶµ
    -0.21
    irus
    -0.20
    åħ¨éķ¿
    -0.19
    èģĶ社
    -0.19
    ä¾Ľè´§
    -0.19
    èµĽåŃ£
    -0.19
    åĪĨ享
    -0.19
    ç«ŀæĬĢ
    -0.19
    /engine
    -0.19
    æ¯ģçģŃ
    -0.18
    POSITIVE LOGITS
    丰å¯Į
    0.25
    é¢ľèī²
    0.22
     colors
    0.22
    è±IJå¯Į
    0.21
     деÑĢ
    0.20
    çķĻä½ı
    0.19
    丰å¯ĮçļĦ
    0.19
     millions
    0.19
     memory
    0.19
    colors
    0.19
    Activations Density 0.015%

    No Known Activations