© 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. 50152
    Prev
    Next
    INDEX
    Explanations

    robotic arm or manipulators

    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
    åĴĮåıijå±ķ
    -0.07
    adera
    -0.07
    obl
    -0.06
    ä¸İåıijå±ķ
    -0.06
    ures
    -0.06
     olor
    -0.06
    çĨŁ
    -0.06
    ç´¢éģĵ
    -0.06
    awe
    -0.06
    oral
    -0.06
    POSITIVE LOGITS
    arium
    0.09
    omy
    0.08
    ics
    0.08
    RIO
    0.08
    (robot
    0.08
    onomous
    0.08
    -ass
    0.08
    ημα
    0.08
    -human
    0.08
    cules
    0.08
    Activations Density 0.046%

    No Known Activations