© 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. 558
    Prev
    Next
    INDEX
    Explanations

    medical, scientific, or academic contexts

    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
    enson
    -0.23
    _SR
    -0.23
    ksen
    -0.23
    ationToken
    -0.23
    æµĵåİļ
    -0.22
    侬
    -0.22
    .vaadin
    -0.21
    DU
    -0.21
    æµĵæµĵçļĦ
    -0.21
    _LR
    -0.21
    POSITIVE LOGITS
    Timeline
    0.24
    archical
    0.23
    ä¼ĺ
    0.22
    å°¼åħĭ
    0.22
    ILES
    0.22
    Runnable
    0.21
    çĬ¶
    0.21
    æĸŁ
    0.21
     essentially
    0.21
    åģļçļĦäºĭæĥħ
    0.21
    Activations Density 0.739%

    No Known Activations