© 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. 2094
    Prev
    Next
    INDEX
    Explanations

    Archbishop of

    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
    åŃIJéĩĮ
    -0.22
    æŶéĹ´åĨħ
    -0.20
    工夫
    -0.20
    arme
    -0.19
    çĹķ
    -0.19
     primitive
    -0.19
    为æĤ¨æıIJä¾Ľ
    -0.19
     pedal
    -0.19
    .camel
    -0.18
    ãģĵãģ¨
    -0.18
    POSITIVE LOGITS
    ÑĮе
    0.24
    endas
    0.23
    urations
    0.23
    ÑĮÑı
    0.23
    ission
    0.22
    itect
    0.22
    aic
    0.21
    dale
    0.21
    -quarters
    0.21
    sz
    0.21
    Activations Density 0.008%

    No Known Activations