© 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. 34097
    Prev
    Next
    INDEX
    Explanations

    software license

    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
     [-]:
    -0.10
    [âĢ¦
    -0.09
    ÖĦ
    -0.09
    npos
    -0.09
    beauf
    -0.09
     UIAlert
    -0.08
    DMETHOD
    -0.08
    Uvs
    -0.08
    åħ¨å±ıæŁ¥çľĭ
    -0.08
    à·ģ
    -0.08
    POSITIVE LOGITS
    1
    0.07
    2
    0.07
    3
    0.07
    7
    0.07
    5
    0.07
    6
    0.06
    8
    0.06
    otope
    0.06
    IP
    0.06
    4
    0.05
    Activations Density 0.026%

    No Known Activations