© 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. 16327
    Prev
    Next
    INDEX
    Explanations

    makeover, intervention, shoot, Wish, First

    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
    渴
    -0.21
    åĢĴ
    -0.20
    没åķ¥
    -0.20
    åĿļæŀľ
    -0.20
    讲è¯Ŀ
    -0.19
    æĤłéĹ²
    -0.19
    _ctl
    -0.18
    èĬ½
    -0.18
    说å®ŀ
    -0.18
    é§IJ
    -0.18
    POSITIVE LOGITS
    OLA
    0.21
    礼çī©
    0.20
     bisc
    0.20
    æĶ¹åıĺ
    0.19
    osos
    0.19
    /change
    0.18
    ç»ĵå±Ģ
    0.18
    å¼Ģåĩº
    0.18
    emed
    0.18
    æ¯Ľ
    0.17
    Activations Density 0.003%

    No Known Activations