© 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. 23545
    Prev
    Next
    INDEX
    Explanations

    IRT, lunar, natural, relationship, log

    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
    xCC
    -0.10
    ç¾İä¸Ń
    -0.09
    eshire
    -0.09
    ardy
    -0.09
    .XR
    -0.09
    XD
    -0.09
    çĽ¸ä¼¼æĸĩçĮ®
    -0.08
     Amat
    -0.08
    reven
    -0.08
    ếm
    -0.08
    POSITIVE LOGITS
     Thomson
    0.07
    1
    0.07
    ^
    0.07
    çī¹å®ļ
    0.07
     measured
    0.07
     purified
    0.06
    åľ¨è§Ħå®ļ
    0.06
    ç»ıè¿ĩ
    0.06
    0.06
    actly
    0.06
    Activations Density 0.016%

    No Known Activations