© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21764
    Prev
    Next
    INDEX
    Explanations

    force needed or vector

    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
    éķ¿æ²³
    -0.07
    arer
    -0.07
    å¡ĹãĤĬ
    -0.07
    ebro
    -0.06
    æĪIJæ´»
    -0.06
     Covered
    -0.06
    blink
    -0.06
    ziem
    -0.06
    klus
    -0.06
     slate
    -0.06
    POSITIVE LOGITS
    åĬĽçļĦ
    0.12
     force
    0.11
    åĬĽåĴĮ
    0.11
    force
    0.11
    -force
    0.11
     Force
    0.10
    (force
    0.10
    åĬĽ
    0.10
     exert
    0.10
     magnitude
    0.09
    Activations Density 0.005%

    No Known Activations