© 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. 42117
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or 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
    oland
    -0.10
    天çĽĸ
    -0.09
    ARSE
    -0.08
    ä¸įæ²»
    -0.08
    /place
    -0.08
    éļĶéĽ¢
    -0.08
    åħ¶å¯¹
    -0.08
    abbr
    -0.08
    adrid
    -0.08
    áºł
    -0.08
    POSITIVE LOGITS
    Âł
    0.07
    b
    0.07
    鼶鼶
    0.06
    ³³³
    0.06
     section
    0.06
    :
    0.06
    æ´²
    0.06
    âĢ§
    0.06
    âĶĢ
    0.06
    R
    0.06
    Activations Density 0.133%

    No Known Activations