© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2199
    Prev
    Next
    INDEX
    Explanations

    open doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     amenities
    -0.25
    éĢļè¡Į
    -0.24
    为æ°ij
    -0.24
    æĪĸå¤ļæĪĸå°ij
    -0.24
    å®ļå±ħ
    -0.24
    æĹ©æĻļ
    -0.24
    ä¸įå®ļ
    -0.24
    建设åĴĮ
    -0.23
     *(*
    -0.23
    é¢ĦæĬ¥
    -0.22
    POSITIVE LOGITS
     incred
    0.24
    éĵ¿
    0.23
     notebook
    0.22
    PT
    0.22
    ä¸ĭè¾¾
    0.22
    Neill
    0.22
     plat
    0.22
     scri
    0.21
    è·Łä»ĸ
    0.21
    颤æĬĸ
    0.21
    Activations Density 0.030%

    No Known Activations