© 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. 1319
    Prev
    Next
    INDEX
    Explanations

    suffix

    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
    å·¨æĺŁ
    -0.07
    ampton
    -0.07
    avier
    -0.07
    >(*
    -0.06
     nad
    -0.06
    aires
    -0.06
    kaw
    -0.06
    大水
    -0.06
    antha
    -0.06
    ÙĨÛĮÙĨ
    -0.06
    POSITIVE LOGITS
     eds
    0.09
     Subcommittee
    0.08
    resa
    0.08
     Handbook
    0.08
     handbook
    0.08
    itter
    0.07
    è¿Ľä¸ĢæŃ¥æĺİç¡®
    0.07
     homers
    0.07
    brief
    0.07
    ligh
    0.07
    Activations Density 0.030%

    No Known Activations