© 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. 9754
    Prev
    Next
    INDEX
    Explanations

    abstract, indulge, benefiting, opted, inquire, marvel, experiment

    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
    hta
    -0.08
    oba
    -0.08
    edImage
    -0.08
    edList
    -0.07
    itre
    -0.07
    ãģ£ãģĭãģij
    -0.07
    edig
    -0.07
    ÙĪÙĩا
    -0.07
     Spor
    -0.07
    pper
    -0.07
    POSITIVE LOGITS
    äºİ
    0.12
    äºİä¸Ģ
    0.10
    äºİæѤ
    0.09
    äºİè¡Į
    0.09
    åħ³äºİ
    0.09
    äºİå¿ĥ
    0.09
    äºİ人
    0.08
     on
    0.08
     about
    0.08
    äºİäºĭ
    0.08
    Activations Density 0.622%

    No Known Activations