© 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. 15428
    Prev
    Next
    INDEX
    Explanations

    isotope compositions

    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
    åľ¨æµ·
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
     bè
    -0.07
    שת
    -0.07
    è¤
    -0.07
    SI
    -0.06
    /inet
    -0.06
    ÙĬÙħÙĬ
    -0.06
    .ix
    -0.06
    ombat
    -0.06
    POSITIVE LOGITS
    äºijå±±
    0.08
    åĴĮå¦Īå¦Ī
    0.08
    resp
    0.08
    åĴĮ第äºĮ
    0.07
    åĴĮäºĮ
    0.07
    æķ¬
    0.07
    ofil
    0.07
    å¹
    0.07
    çĮ
    0.07
    åĴĮ红
    0.07
    Activations Density 0.212%

    No Known Activations