© 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. 26353
    Prev
    Next
    INDEX
    Explanations

    past or previous concepts

    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
    ä¸İåħ±
    -0.08
    ÏİÏģα
    -0.08
    YRO
    -0.08
    abcdefghijklmnopqrstuvwxyz
    -0.08
    æĺ¯ä¸Ģé¢Ĺ
    -0.07
    ymas
    -0.07
    ivio
    -0.07
    KER
    -0.07
    ILLS
    -0.07
    å°Ĩå°±
    -0.07
    POSITIVE LOGITS
     older
    0.09
    è¿ĩåİ»çļĦ
    0.08
     recurrence
    0.07
     previous
    0.07
     past
    0.07
    ero
    0.07
    éģ
    0.07
     попеÑĢед
    0.07
    èĢģä¸ī
    0.07
     Older
    0.07
    Activations Density 0.006%

    No Known Activations