© 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. 1522
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or code

    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
    ,
    -0.07
    acken
    -0.06
    éĢī
    -0.06
    asher
    -0.06
    è¿Ļæł·ä¸Ģ个
    -0.06
    çļĦä¸Ģ个
    -0.06
    -
    -0.06
    —
    -0.05
    éĢļ常æĥħåĨµä¸ĭ
    -0.05
     extent
    -0.05
    POSITIVE LOGITS
     zaÅĽ
    0.10
    åĪĻæĺ¯
    0.10
     thereafter
    0.10
    åīĩæĺ¯
    0.09
    亦çĦ¶
    0.09
     pedig
    0.09
    ä½ľåĪĻ
    0.09
    åĪĻ为
    0.09
    erdem
    0.09
    çı
    0.09
    Activations Density 0.028%

    No Known Activations