© 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. 61971
    Prev
    Next
    INDEX
    Explanations

    institutional affiliations and funding

    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
    abia
    -0.11
    ulia
    -0.08
    åĪ°èĢģ
    -0.08
    æĺłå°Ħ
    -0.08
    plier
    -0.07
    óc
    -0.07
    Ø´Ùģ
    -0.07
    dro
    -0.07
     Certa
    -0.07
    .zone
    -0.07
    POSITIVE LOGITS
     grate
    0.07
     acknow
    0.07
    å¤Ħ以
    0.07
     permis
    0.07
     affiliated
    0.07
    å¾Īé«ĺåħ´
    0.06
    çī¹æѤ
    0.06
    åĬ©
    0.06
    é²²
    0.06
     acknowledge
    0.06
    Activations Density 0.162%

    No Known Activations