© 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. 62395
    Prev
    Next
    INDEX
    Explanations

    url path separators and codes

    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
    izon
    -0.09
    iliz
    -0.09
    plib
    -0.09
    ãĤĪãĤįãģĹãģıãģĬé¡ĺãģĦ
    -0.09
    äºĭäºĨ
    -0.08
    çķħæĥ³
    -0.08
    ibs
    -0.08
     standa
    -0.08
    anas
    -0.08
    äºĮåįģ大
    -0.08
    POSITIVE LOGITS
    m
    0.06
    åĹ£
    0.06
    mans
    0.06
    à§įথ
    0.06
    ucc
    0.05
    ault
    0.05
    Âł
    0.05
     variant
    0.05
     Ghi
    0.05
    js
    0.05
    Activations Density 0.049%

    No Known Activations