© 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. 1773
    Prev
    Next
    INDEX
    Explanations

    idol, famous people, or inspirations

    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
    ApiClient
    -0.23
    orgia
    -0.23
     sexo
    -0.23
    Categories
    -0.22
    çݯæ¯Ķ
    -0.22
    .addColumn
    -0.21
     Counsel
    -0.21
    ä¸įçķĻ
    -0.21
     subTitle
    -0.21
    OUN
    -0.21
    POSITIVE LOGITS
    åIJijå¾Ģ
    0.39
     famous
    0.39
     reputation
    0.39
     reput
    0.35
    æĨ§
    0.34
    éĹ»åIJį
    0.34
     legendary
    0.34
    å´ĩæĭľ
    0.33
    æłĩå¿ĹæĢ§
    0.33
     fan
    0.31
    Activations Density 0.129%

    No Known Activations