© 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. 8170
    Prev
    Next
    INDEX
    Explanations

    confirmation and identification

    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
    orma
    -0.07
    obra
    -0.07
    raits
    -0.06
    è¯Ĺæĥħ
    -0.06
    .off
    -0.06
    å¦Ĥä½ķéĢīæĭ©
    -0.06
     soggi
    -0.06
    _terms
    -0.06
    жин
    -0.06
    åı¯æĥľçļĦæĺ¯
    -0.06
    POSITIVE LOGITS
     confirmed
    0.14
    æĹłè¯¯
    0.14
    confirmed
    0.12
     confirming
    0.12
    确认
    0.12
    Confirmed
    0.12
     unmistak
    0.12
     verified
    0.11
     authenticity
    0.11
     Confirm
    0.11
    Activations Density 0.312%

    No Known Activations