© 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. 19633
    Prev
    Next
    INDEX
    Explanations

    .Float state assignment or enumeration

    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
    审
    -0.06
    é«ĺæ°Ķ
    -0.06
    ulares
    -0.06
    files
    -0.06
    èŃĺ
    -0.06
    館
    -0.06
    pte
    -0.06
    åħļç»Ħ书记
    -0.06
    _root
    -0.06
    à¸įา
    -0.06
    POSITIVE LOGITS
    èijĽ
    0.09
    enten
    0.08
     Gep
    0.08
    第ä¸ī个
    0.08
     âĶľâĶĢâĶĢ
    0.07
    ç¬¬åĽĽä¸ª
    0.07
    ẹp
    0.07
    entar
    0.07
    kest
    0.07
    odore
    0.07
    Activations Density 0.027%

    No Known Activations