© 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. 40123
    Prev
    Next
    INDEX
    Explanations

    terminal blocks or devices

    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
    ़
    -0.09
    öder
    -0.08
    纷åijĪ
    -0.07
    é¢ĺæĦı
    -0.07
    ترض
    -0.07
    é¢ĺå¹²
    -0.07
    หมาย
    -0.07
    pper
    -0.07
    ../../
    -0.07
    çľĭåĪ°è¿ĻéĩĮ
    -0.07
    POSITIVE LOGITS
    ized
    0.10
    ¯
    0.09
    sWith
    0.09
    izing
    0.09
    ization
    0.08
    ities
    0.08
    -most
    0.08
    reich
    0.08
    idade
    0.08
    idad
    0.08
    Activations Density 0.015%

    No Known Activations