© 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. 49020
    Prev
    Next
    INDEX
    Explanations

    previous / past / behind

    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
    .shuffle
    -0.08
     Def
    -0.07
    Def
    -0.06
    ign
    -0.06
     def
    -0.06
     Wade
    -0.06
     Alic
    -0.06
    æµ®äºij
    -0.06
     meas
    -0.06
    é£ĺ
    -0.06
    POSITIVE LOGITS
    (prev
    0.09
    _prev
    0.09
    arness
    0.09
    äºĨè¿ĩåİ»
    0.08
    è¿ĩåİ»
    0.08
     пÑĢедÑĭ
    0.08
     previous
    0.08
    previous
    0.08
    æĽ´æĸ°
    0.08
     past
    0.08
    Activations Density 0.003%

    No Known Activations