© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47421
    Prev
    Next
    INDEX
    Explanations

    if you ask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    สวà¸Ļ
    -0.08
     safer
    -0.08
     safest
    -0.07
    èĭ¥æĹł
    -0.07
    textbox
    -0.07
    次
    -0.07
    è¯ķåĽ¾
    -0.07
    æľĢéľĢè¦ģ
    -0.07
    Should
    -0.07
    safe
    -0.07
    POSITIVE LOGITS
     properly
    0.15
     appropriately
    0.14
    å¾Ĺå½ĵ
    0.13
     carefully
    0.12
     proper
    0.12
    proper
    0.12
     adequately
    0.12
    éĢĤå½ĵçļĦ
    0.12
     Proper
    0.12
    éĢĤå½ĵ
    0.12
    Activations Density 0.210%

    No Known Activations