© 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. 2122
    Prev
    Next
    INDEX
    Explanations

    examples

    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
    erness
    -0.22
    ä¸Ģ个å¤ļ
    -0.21
    est
    -0.20
    çĦ¶æĺ¯
    -0.19
    å¾Ĺä½ı
    -0.18
    erview
    -0.18
    edelta
    -0.18
    EXPECT
    -0.18
    amel
    -0.18
    estring
    -0.18
    POSITIVE LOGITS
    ise
    0.28
    OfWork
    0.27
    sto
    0.26
    /example
    0.24
    wise
    0.24
    atic
    0.24
    é¦Ĩ
    0.23
    hood
    0.23
    strate
    0.21
    -wise
    0.21
    Activations Density 0.079%

    No Known Activations