© 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. 62168
    Prev
    Next
    INDEX
    Explanations

    resistance, conductance, and series

    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
     Subset
    -0.08
    两ä¸į误
    -0.07
    dent
    -0.07
     coloring
    -0.07
     Caught
    -0.06
    _xor
    -0.06
    zam
    -0.06
    icolor
    -0.06
     caught
    -0.06
    SelectionMode
    -0.06
    POSITIVE LOGITS
    éĺ»
    0.12
    éĺ»åĬĽ
    0.10
     resistance
    0.10
    çݯèĬĤçļĦ
    0.10
    çݯèĬĤ
    0.09
    串èģĶ
    0.09
     imped
    0.09
    éĺ»éļĶ
    0.09
    Resistance
    0.08
    åĪĨ段
    0.08
    Activations Density 0.002%

    No Known Activations