© 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. 18975
    Prev
    Next
    INDEX
    Explanations

    bacterial names ending in -ens, -us, -ida, -id

    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
    ä¾
    -0.07
    å°Ķå¾·
    -0.06
    对åĨħ
    -0.06
    ÙħØŃ
    -0.06
    ombs
    -0.06
     Chapman
    -0.06
    æŀĦçŃijçī©
    -0.06
    好ä¸į容æĺĵ
    -0.06
    ä¸Ńä»ĭæľºæŀĦ
    -0.06
     analogue
    -0.06
    POSITIVE LOGITS
     unspecified
    0.09
    etros
    0.08
    æľīå¾Īå¤ļç§į
    0.08
     ê³ĦìĹ´
    0.08
    ÄĽk
    0.08
    éĭĴ
    0.08
    neos
    0.07
    pty
    0.07
    çĶ¨éĢĶ
    0.07
     unidentified
    0.07
    Activations Density 0.159%

    No Known Activations