© 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. 57956
    Prev
    Next
    INDEX
    Explanations

    threshold voltage or temperature

    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
    ä¸Ńæĸ¹
    -0.08
    nnen
    -0.07
    roe
    -0.07
    istri
    -0.07
    деÑĤÑĮ
    -0.07
    åĭĺ
    -0.07
    leftright
    -0.07
    /text
    -0.07
    ãģ«éĻIJ
    -0.07
    OutOf
    -0.07
    POSITIVE LOGITS
    èĮĥåĽ´ä¹ĭåĨħ
    0.09
    éĻĦè¿ij
    0.09
    大åħ³
    0.08
    ä»ĺè¿ij
    0.08
     hinaus
    0.08
     vicinity
    0.07
    éĻĦè¿ijçļĦ
    0.07
    ank
    0.07
    为æŃ¢
    0.07
    èĮĥåĽ´åĨħçļĦ
    0.07
    Activations Density 0.036%

    No Known Activations