© 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. 61688
    Prev
    Next
    INDEX
    Explanations

    numbers, hash, McBride

    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
    çŁ
    -0.08
     Hayes
    -0.07
    veis
    -0.07
    æĪijè¦ģè¯Ħ论
    -0.07
    éĵ¾
    -0.07
    åħ¼æĢ»ç»ıçIJĨ
    -0.07
    天å®Ŀ
    -0.07
     spis
    -0.07
    -auto
    -0.07
     GiÃł
    -0.07
    POSITIVE LOGITS
    Ó©Ó©
    0.07
     tslint
    0.07
    fen
    0.06
    _conf
    0.06
    fter
    0.06
    å¸ĮæľĽåı¯ä»¥
    0.06
    åį³åĪ°
    0.06
    oment
    0.06
     Pisc
    0.06
    amp
    0.06
    Activations Density 0.067%

    No Known Activations