© 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. 64307
    Prev
    Next
    INDEX
    Explanations

    values and receiving values

    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
    ostro
    -0.07
    etti
    -0.07
     Daya
    -0.07
    åŁºç¡ĢæĢ§
    -0.07
    uÄĩ
    -0.07
    æĺµ
    -0.07
    èĢĮåħ¥
    -0.07
    åij¨å¹´æħ¶
    -0.07
    éĹ·
    -0.07
    anka
    -0.07
    POSITIVE LOGITS
    åĪĹ举
    0.07
    å¦ĤæľŁ
    0.07
    llx
    0.07
    arna
    0.07
    (levels
    0.07
    åĪĹåĩº
    0.07
    æ»
    0.06
     listed
    0.06
    è¤
    0.06
    æ³¾
    0.06
    Activations Density 0.005%

    No Known Activations