© 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. 24016
    Prev
    Next
    INDEX
    Explanations

    ], }, );

    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
    <|quad_end|>
    -0.09
    iché
    -0.09
    /fw
    -0.08
    証åĪ¸
    -0.08
     غÙĬرÙĩا
    -0.07
    orman
    -0.07
     Newtown
    -0.07
    强ä¼ģä¸ļ
    -0.07
    ä¸Ģ件äºĭæĥħ
    -0.07
    ambi
    -0.07
    POSITIVE LOGITS
    رد
    0.07
    èĢĥè¯ķçļĦ
    0.06
    ä¸įèĩªè§ī
    0.06
    plom
    0.06
    ä¾Ŀ次为
    0.06
    ä¾Ŀ次
    0.06
    Overrides
    0.06
    azos
    0.06
    idang
    0.06
    üte
    0.06
    Activations Density 0.003%

    No Known Activations