© 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. 1566
    Prev
    Next
    INDEX
    Explanations

    empty arrays or nothing

    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
    缸åħ³èµĦ讯
    -0.07
     á»ķ
    -0.07
    çĺŁ
    -0.07
    bic
    -0.07
    èĮ¸
    -0.07
    _aliases
    -0.07
    æħ¢
    -0.07
     otr
    -0.07
    erner
    -0.06
    हि
    -0.06
    POSITIVE LOGITS
    ([]
    0.09
    isEmpty
    0.09
    EMPTY
    0.08
     EMPTY
    0.08
     empty
    0.08
    ä»Ģä¹Īéĥ½æ²¡æľī
    0.08
    .isEmpty
    0.08
    empty
    0.08
    =[]
    0.08
    é¢ĺå¹²
    0.08
    Activations Density 0.015%

    No Known Activations