© 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. 48112
    Prev
    Next
    INDEX
    Explanations

    JavaScript function documentation comments and code examples

    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
    pis
    -0.08
    èº
    -0.08
    æĭĿ
    -0.08
    è·»
    -0.08
    ÃģP
    -0.08
     realise
    -0.07
     altrett
    -0.07
    NotAllowed
    -0.07
    aper
    -0.07
    éĶ¤
    -0.07
    POSITIVE LOGITS
    Ïģγ
    0.06
    asan
    0.06
    .chrome
    0.06
    udents
    0.06
    ench
    0.06
    omb
    0.06
    ught
    0.06
    æģ©åħ¸
    0.06
     rest
    0.05
    å½¢èī²
    0.05
    Activations Density 0.004%

    No Known Activations