© 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. 7350
    Prev
    Next
    INDEX
    Explanations

    separating separate items

    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
    æķ´
    -0.08
    绣ä¸Ģ
    -0.08
    绣
    -0.08
     centrally
    -0.07
    绣ä¸ĢçļĦ
    -0.07
    ataka
    -0.07
    ä¸Ģæķ´
    -0.07
    ä»»ä½ķä¸Ģç§į
    -0.07
    ä½ľåĵģåĨħ容
    -0.07
    ä¸Ģè´¯
    -0.07
    POSITIVE LOGITS
     separate
    0.24
    åĪĨå¼Ģ
    0.23
     Separate
    0.23
    åĪĨ离
    0.22
    Separ
    0.22
     separation
    0.21
     separated
    0.21
     seperate
    0.20
     separating
    0.20
     separ
    0.19
    Activations Density 0.364%

    No Known Activations