© 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. 13928
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or punctuation

    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¸įå¿ĺ
    -0.18
    æ»ij
    -0.18
    Threads
    -0.17
    iams
    -0.17
    anel
    -0.16
    <body
    -0.16
    ODB
    -0.16
    åī½
    -0.16
    erte
    -0.16
    ctors
    -0.16
    POSITIVE LOGITS
    æħ°éĹ®
    0.19
    大éĺŁ
    0.18
    è¡ĮåĬ¨è®¡åĪĴ
    0.18
    á»įng
    0.18
    ç£
    0.17
    è¡ĮæĶ¿æī§æ³ķ
    0.17
    磶
    0.17
    ç®ĹäºĨ
    0.17
     EOF
    0.16
    縱
    0.16
    Activations Density 0.435%

    No Known Activations