© 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. 38307
    Prev
    Next
    INDEX
    Explanations

    academic fields

    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
    izer
    -0.06
    å®ļ为
    -0.06
    z
    -0.06
    dot
    -0.06
    ung
    -0.06
     pilot
    -0.06
    çĤŃ
    -0.05
     trick
    -0.05
    è¾¹
    -0.05
     dot
    -0.05
    POSITIVE LOGITS
    -kit
    0.08
    eningen
    0.08
    orneys
    0.08
    envir
    0.08
    egah
    0.08
    .uc
    0.08
    itemap
    0.07
    icola
    0.07
     Ø´ÙĨ
    0.07
    æĤ¨å½ĵåīįçļĦä½įç½®
    0.07
    Activations Density 0.030%

    No Known Activations