© 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. 2356
    Prev
    Next
    INDEX
    Explanations

    produce business

    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
    OrUpdate
    -0.26
    ingly
    -0.22
    uba
    -0.21
     proactive
    -0.21
    ä¸ªå·¥ä½ľ
    -0.21
    _compute
    -0.21
    ierarchical
    -0.21
    ether
    -0.21
    erea
    -0.20
    äºĨä¸Ģ个
    -0.20
    POSITIVE LOGITS
    -covered
    0.24
     natur
    0.22
    /mac
    0.21
    aqu
    0.21
     Manip
    0.20
    hell
    0.20
    /math
    0.20
     Everywhere
    0.20
    /apple
    0.20
     shopping
    0.20
    Activations Density 0.001%

    No Known Activations