© 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. 15931
    Prev
    Next
    INDEX
    Explanations

    either or opposite

    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
    ankind
    -0.07
    å¾·éĩĮ
    -0.07
    araf
    -0.07
    åĨħç½®
    -0.07
    icc
    -0.07
    è¿ĻäºĽä¸ľè¥¿
    -0.06
    ãĥĨãĥ³
    -0.06
     desac
    -0.06
    çĶ¨å®ĥ
    -0.06
    å±Ģéĥ¨
    -0.06
    POSITIVE LOGITS
    æ¸ħçĻ½
    0.08
    æݨæĸŃ
    0.08
    æݨæµĭ
    0.07
    Scenario
    0.07
     obja
    0.07
    大èĥĨçļĦ
    0.07
     explan
    0.07
     unlucky
    0.07
    åıªèĥ½éĢļè¿ĩ
    0.07
    ç¿»äºĨ
    0.07
    Activations Density 0.007%

    No Known Activations