© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30196
    Prev
    Next
    INDEX
    Explanations

    false alarms and positives

    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
    oten
    -0.07
    iox
    -0.07
    бий
    -0.07
    æIJŀ好
    -0.06
    سخ
    -0.06
    TL
    -0.06
     Lans
    -0.06
    éĿŀå¾Ĺ
    -0.06
    дио
    -0.06
    omod
    -0.06
    POSITIVE LOGITS
     false
    0.14
    false
    0.14
    /false
    0.13
    False
    0.13
     False
    0.12
    åģĩçļĦ
    0.12
     falsely
    0.12
    误
    0.11
    FALSE
    0.11
     FALSE
    0.11
    Activations Density 0.104%

    No Known Activations