© 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. 7869
    Prev
    Next
    INDEX
    Explanations

    heavy metals, heavy-duty, heavy lifting

    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
    ÙĥÙĬÙħ
    -0.09
    ذاÙĥ
    -0.09
    ë¦Ħ
    -0.09
    OrElse
    -0.09
    à¸Ķาย
    -0.08
    ÑĪон
    -0.08
     voto
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    大åĵŃ
    -0.08
    oweit
    -0.08
    POSITIVE LOGITS
    ening
    0.09
    elijk
    0.07
    asm
    0.07
    å¦Ĥå±±
    0.07
    manship
    0.07
    ened
    0.07
    uage
    0.07
    æĥħåĨµä¸ĭ
    0.06
    te
    0.06
    åħ¶äºĭ
    0.06
    Activations Density 0.012%

    No Known Activations