© 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. 14881
    Prev
    Next
    INDEX
    Explanations

    definition or refers to

    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
    asurer
    -0.23
     пÑģ
    -0.21
    ipeg
    -0.20
    ç®Ķ
    -0.20
    çļĦä½įç½®
    -0.19
    ONGL
    -0.19
    éĴ³
    -0.19
    mare
    -0.18
    lain
    -0.18
    _AdjustorThunk
    -0.18
    POSITIVE LOGITS
     definition
    0.25
    èĢ·
    0.23
    åŃ³
    0.22
    å®ļä¹ī
    0.22
     Definition
    0.22
    éĢļ常
    0.22
    ä¸ĢèĪ¬æĿ¥è¯´
    0.22
    Definition
    0.21
    æľīå¾Īå¤ļç§į
    0.21
     defined
    0.20
    Activations Density 0.228%

    No Known Activations