© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 576
    Prev
    Next
    INDEX
    Explanations

    after to

    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
    ä¸Ģç§į
    -0.25
    ä¸ĢæŃ¥æŃ¥
    -0.25
    çļĦä¸Ģç§į
    -0.24
    ä¸ĢçĤ¹çĤ¹
    -0.23
    elib
    -0.23
    ð¬±ĸ
    -0.23
    ä¿į
    -0.23
    datasets
    -0.23
     events
    -0.23
    BOR
    -0.23
    POSITIVE LOGITS
    æIJŀå®ļ
    0.25
    èŁ¾
    0.25
    æĪĸå¤ļ
    0.24
    -worthy
    0.23
     straight
    0.22
     stead
    0.22
    -back
    0.22
     followed
    0.22
    泪
    0.22
    æµ´
    0.22
    Activations Density 0.058%

    No Known Activations