© 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. 1030
    Prev
    Next
    INDEX
    Explanations

    code creation from objects

    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
     stale
    -0.06
    å®Ī
    -0.06
    ofil
    -0.06
    çĭ©
    -0.06
    ä¸į欲
    -0.06
    èĻij
    -0.06
    _tpl
    -0.05
    广è§Ĵ
    -0.05
    åĸľæ¬¢çľĭ
    -0.05
    缸
    -0.05
    POSITIVE LOGITS
    .createFrom
    0.11
     recreate
    0.10
    åĪĽå»ºçļĦ
    0.10
    åĪĽå»º
    0.10
    FromString
    0.09
    reate
    0.09
     recre
    0.09
    åīµå»º
    0.09
    ç»Ħ建
    0.08
    stantiate
    0.08
    Activations Density 0.022%

    No Known Activations