© 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. 55612
    Prev
    Next
    INDEX
    Explanations

    prob of picking/sequence

    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
    landen
    -0.07
    ieno
    -0.07
    æ¾Ħ
    -0.06
    åĦ¿
    -0.06
     isFirst
    -0.06
    åľ£äºº
    -0.06
    à¤Ĥà¤ķ
    -0.06
    çĿĢä¸Ģé¢Ĺ
    -0.06
    OLT
    -0.06
    asso
    -0.06
    POSITIVE LOGITS
    DIC
    0.08
    ERV
    0.08
    achim
    0.08
    åįĹè·¯
    0.07
    _TRY
    0.07
    è·ijäºĨ
    0.07
    溫
    0.07
    ewidth
    0.07
     Vig
    0.07
     modeller
    0.07
    Activations Density 0.042%

    No Known Activations