© 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. 20224
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    elin
    -0.08
    zsche
    -0.08
    ault
    -0.08
    ovit
    -0.07
    ocrates
    -0.07
    ugg
    -0.07
    zego
    -0.07
    essen
    -0.07
    iken
    -0.07
    %A
    -0.07
    POSITIVE LOGITS
    imid
    0.08
    oping
    0.07
    ensiva
    0.07
    äºİæѤ
    0.07
    yssey
    0.07
    ÙĨÙĩ
    0.07
    -END
    0.07
    worm
    0.07
    ÙĦÙĩ
    0.07
    urement
    0.07
    Activations Density 0.005%

    No Known Activations