© 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. 25391
    Prev
    Next
    INDEX
    Explanations

    formationally

    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
    ted
    -0.08
    ãĤĪãģĨãģª
    -0.08
    ened
    -0.07
    ows
    -0.07
    পà§ģর
    -0.07
    -funded
    -0.06
    burgh
    -0.06
    enburg
    -0.06
    going
    -0.06
    缸è¾ħ缸æĪIJ
    -0.06
    POSITIVE LOGITS
    ally
    0.09
    ewise
    0.09
    ä¸İä½ľçĶ¨
    0.08
     waarin
    0.08
    TRL
    0.08
    /activity
    0.08
    ä¸įä½³
    0.08
    åIJĦå¼Ĥ
    0.08
    ä¸ĩåįĥ
    0.08
    spb
    0.07
    Activations Density 0.017%

    No Known Activations