© 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. 1485
    Prev
    Next
    INDEX
    Explanations

    partnered with

    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
    Invite
    -0.24
    aney
    -0.23
     пÑĢоиÑģ
    -0.23
    ä¸Ģå¹ķ
    -0.23
     reliance
    -0.22
     grosse
    -0.22
    ä»ĸ们æĺ¯
    -0.22
    ICIAL
    -0.22
    -contact
    -0.22
    快讯
    -0.22
    POSITIVE LOGITS
     West
    0.26
     Bro
    0.26
     Cook
    0.24
     Dou
    0.24
     hospitals
    0.23
     Bo
    0.23
     Ro
    0.23
     Ca
    0.23
     local
    0.23
     several
    0.23
    Activations Density 0.037%

    No Known Activations