© 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. 42063
    Prev
    Next
    INDEX
    Explanations

    splitting, breaking, or dividing

    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
    ulia
    -0.09
    -describedby
    -0.08
    lesa
    -0.08
     Assigned
    -0.08
     اÙĦÙħتر
    -0.08
    acobian
    -0.07
    _EXTENSIONS
    -0.07
    jou
    -0.07
    -Am
    -0.07
    zcze
    -0.07
    POSITIVE LOGITS
    å¤Ħ
    0.10
     separating
    0.09
    åĪĨéļĶ
    0.09
     splits
    0.08
    ä½įç½®
    0.08
    å¤ĦçļĦ
    0.08
    between
    0.08
    æĸŃå¼Ģ
    0.07
     location
    0.07
     dividing
    0.07
    Activations Density 0.037%

    No Known Activations