© 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. 18673
    Prev
    Next
    INDEX
    Explanations

    data type conversions

    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
    betrieb
    -0.08
    serter
    -0.08
    åİĨ代
    -0.08
    HashCode
    -0.08
    åķĨæłĩä¿¡æģ¯
    -0.07
    å¤Ħéķ¿
    -0.07
     Gründ
    -0.07
    bury
    -0.07
    ynes
    -0.07
    ATORY
    -0.07
    POSITIVE LOGITS
    subtype
    0.09
    ç±»åĪ«
    0.08
    _subtype
    0.08
     datatype
    0.07
     elementType
    0.07
     itemType
    0.07
     subtype
    0.07
    å±ŀæĢ§
    0.07
    å¤ļæł·
    0.07
    çĽ¸å®¹
    0.07
    Activations Density 0.167%

    No Known Activations