© 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. 57407
    Prev
    Next
    INDEX
    Explanations

    ready, disabled, invalid

    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
    ibes
    -0.08
    ibe
    -0.08
    abwe
    -0.07
    беÑĢе
    -0.07
    人åijĺè§Ħ模
    -0.07
    valu
    -0.07
    群ç»Ħ
    -0.07
    ίοÏħ
    -0.07
    oland
    -0.07
     fras
    -0.07
    POSITIVE LOGITS
    åĤ¬
    0.08
    失
    0.07
    就绪
    0.07
    Dependency
    0.07
     ready
    0.07
     Dependency
    0.07
    æļĤç¼ĵ
    0.07
    对éĤ£äºĽ
    0.07
     readiness
    0.07
    以å¾ħ
    0.07
    Activations Density 0.002%

    No Known Activations