© 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. 2735
    Prev
    Next
    INDEX
    Explanations

    causes an outcome

    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
    าะ
    -0.22
     gì
    -0.21
    pedia
    -0.20
    latex
    -0.20
     quoi
    -0.20
    .compareTo
    -0.20
    agem
    -0.20
    ãģĭãģijãģ¦
    -0.20
     flair
    -0.20
    naire
    -0.20
    POSITIVE LOGITS
    ed
    0.24
    ean
    0.23
     latter
    0.20
    çļĨ
    0.20
     cái
    0.20
    ä¹ĭåľ°
    0.20
    å¿ĥæĦ¿
    0.20
    redo
    0.20
    ded
    0.20
     demise
    0.20
    Activations Density 0.041%

    No Known Activations