© 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. 1968
    Prev
    Next
    INDEX
    Explanations

    then [verb]

    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
    å¤Ħå¤Ħ
    -0.07
    æŶæľī
    -0.07
    -notification
    -0.07
    æĿ¥åĩ½
    -0.07
    _notice
    -0.06
     Thread
    -0.06
     Annunci
    -0.06
    欣èµıåĪ°
    -0.06
     пÑĢидеÑĢж
    -0.06
    reads
    -0.06
    POSITIVE LOGITS
    èĩªå·±ä¹Ł
    0.08
    arel
    0.08
    æĬĺ
    0.07
    å¾ĹæĦı
    0.07
    çĶ¨æ³ķ
    0.07
    éal
    0.07
    è¿ĺçĶ¨
    0.07
    êu
    0.07
    _resolve
    0.07
    uria
    0.07
    Activations Density 0.151%

    No Known Activations