© 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. 2625
    Prev
    Next
    INDEX
    Explanations

    Alzheimer's disease

    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
    èĦĨ
    -0.27
    индивид
    -0.23
     Debate
    -0.23
     FileInputStream
    -0.23
    aurus
    -0.21
     startActivityForResult
    -0.21
    稼
    -0.21
     Bomb
    -0.21
    drag
    -0.21
     Drag
    -0.21
    POSITIVE LOGITS
    çŃīè¡Įä¸ļ
    0.24
    edb
    0.23
    sm
    0.23
    s
    0.22
    brook
    0.22
    ymes
    0.22
    离
    0.21
    没éĶĻ
    0.21
     dõ
    0.21
    ship
    0.21
    Activations Density 0.005%

    No Known Activations