© 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. 47804
    Prev
    Next
    INDEX
    Explanations

    voltage, torque, power, friction, acting

    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
    ierer
    -0.08
    ãĥ©ãĥ«
    -0.08
    åłª
    -0.07
    ige
    -0.07
    éĹĨ
    -0.07
    nger
    -0.07
    çľĭå®Į
    -0.07
    cione
    -0.06
    转贴
    -0.06
    ulette
    -0.06
    POSITIVE LOGITS
    åĬŁ
    0.10
    æľīåĬŁ
    0.09
    åģļåĬŁ
    0.08
    æīĢåģļçļĦ
    0.07
    çĦ¦
    0.07
    æ£ł
    0.07
    æĹłåĬŁ
    0.07
    ahu
    0.07
    æīĢåģļ
    0.07
     Mech
    0.07
    Activations Density 0.005%

    No Known Activations