© 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. 55786
    Prev
    Next
    INDEX
    Explanations

    .txt, _path, -router, -form

    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
    "],["
    -0.08
    <tool_response>
    -0.08
    åľ¨èº«è¾¹
    -0.08
    '&&
    -0.08
    oulos
    -0.08
    opia
    -0.08
    ÙħÙĪÙĨ
    -0.08
    ={},
    -0.08
    Porno
    -0.07
    íĮIJ매ê°Ģ
    -0.07
    POSITIVE LOGITS
    æĤį
    0.08
     tai
    0.07
    eral
    0.07
    ersi
    0.06
    ssp
    0.06
    为åģļ好
    0.06
    ASTER
    0.06
    er
    0.06
    æĥķ
    0.05
    èĬĤå¿«ä¹IJ
    0.05
    Activations Density 0.001%

    No Known Activations