© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50265
    Prev
    Next
    INDEX
    Explanations

    indicates or shows

    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
    Äĥn
    -0.09
    以åħįéĢłæĪIJ
    -0.08
    exion
    -0.08
    .addTab
    -0.07
     redak
    -0.07
     domesti
    -0.07
    .mozilla
    -0.07
    elius
    -0.07
    Segue
    -0.07
    èµ·è§ģ
    -0.07
    POSITIVE LOGITS
     indicates
    0.08
     indicating
    0.08
    表æĺİ
    0.08
    indic
    0.07
     signifies
    0.07
     indicate
    0.07
    代表çļĦ
    0.07
    æĦıåij³çĿĢ
    0.07
     literally
    0.06
    表示
    0.06
    Activations Density 0.068%

    No Known Activations