© 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. 63113
    Prev
    Next
    INDEX
    Explanations

    objectives

    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
    ungan
    -0.07
    old
    -0.07
    ãĤ¸ãĥ³
    -0.07
    ommer
    -0.06
     maxlen
    -0.06
    ópolis
    -0.06
     Lune
    -0.06
    мин
    -0.06
     Schle
    -0.06
    请åħĪ
    -0.06
    POSITIVE LOGITS
    evat
    0.07
    éĿ¢åŃĶ
    0.07
    ç§į
    0.07
    å¦Ĥæĺ¯
    0.07
     diz
    0.07
    _hz
    0.07
    éĩįéĩij
    0.07
    =>'
    0.07
    ÑĥÑģÑĤ
    0.07
    valu
    0.06
    Activations Density 0.383%

    No Known Activations