© 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. 8519
    Prev
    Next
    INDEX
    Explanations

    after 'page' or comments

    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
    DMETHOD
    -0.11
    ä¸įåıij
    -0.10
    #End
    -0.09
    åĬłæĭ¿å¤§çļĦ
    -0.09
    ingend
    -0.09
    asaki
    -0.09
    adak
    -0.08
    èĩªå·±çļĦ缮æłĩ
    -0.08
    quirer
    -0.08
    égi
    -0.08
    POSITIVE LOGITS
     /
    0.07
    '
    0.06
     "
    0.06
    "
    0.06
    ble
    0.06
     XXX
    0.06
     ("
    0.06
     xxx
    0.06
    ë
    0.06
     .
    0.06
    Activations Density 0.477%

    No Known Activations