© 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. 24109
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations

    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
     duration
    -0.11
     shortest
    -0.11
     shorter
    -0.10
    æľĢçŁŃ
    -0.10
     durations
    -0.10
    çŁŃçļĦ
    -0.10
     lengths
    -0.09
    æľĢéķ¿
    -0.09
    缩çŁŃ
    -0.09
     shortened
    -0.09
    POSITIVE LOGITS
    è¿ĩé«ĺ
    0.09
     Enumerator
    0.08
    loff
    0.08
    loh
    0.08
    iped
    0.08
    astra
    0.08
    +xml
    0.07
    اظ
    0.07
    è¶Ĭé«ĺ
    0.07
     scalability
    0.07
    Activations Density 0.049%

    No Known Activations