© 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. 42224
    Prev
    Next
    INDEX
    Explanations

    mechanical loads

    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
    飧
    -0.07
    zust
    -0.07
    å¤Ń
    -0.07
    heus
    -0.06
    ospace
    -0.06
    åĩºåĵģ
    -0.06
    spell
    -0.06
    工夫
    -0.06
    rew
    -0.06
     radical
    -0.06
    POSITIVE LOGITS
     loads
    0.10
    èį·è½½
    0.10
    eload
    0.10
    è½½èį·
    0.09
     Loads
    0.09
     Nett
    0.09
    loads
    0.09
     load
    0.09
    ä½ľçĶ¨äºİ
    0.08
    çŁ¢
    0.08
    Activations Density 0.005%

    No Known Activations