© 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. 14522
    Prev
    Next
    INDEX
    Explanations

    validation and desired actions

    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
    oux
    -0.08
    agak
    -0.08
    ç½ijåıĭè¯Ħ论
    -0.07
    marshall
    -0.07
     à¤īतà¥į
    -0.07
    lagt
    -0.07
    úng
    -0.07
    leman
    -0.07
     Isles
    -0.07
    èĪ¬åľ°
    -0.07
    POSITIVE LOGITS
     desired
    0.12
     gewüns
    0.09
    æĥ³è¦ģ
    0.09
    desired
    0.09
    æīĢ欲
    0.09
     Desired
    0.09
    æ¯Ķå¦Ĥ
    0.09
    ä¾ĭå¦Ĥ
    0.09
    ä½łæĥ³
    0.09
    ä½łæĥ³è¦ģ
    0.09
    Activations Density 0.357%

    No Known Activations