© 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. 30930
    Prev
    Next
    INDEX
    Explanations

    local + descriptor

    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
    年头
    -0.09
    éģįéĩİ
    -0.09
    erable
    -0.08
    ormsg
    -0.08
    linger
    -0.08
    éĹ´çĽĺçªģåĩº
    -0.08
    forth
    -0.08
    apura
    -0.08
    ä¼ģæŁ¥æŁ¥
    -0.08
    notated
    -0.08
    POSITIVE LOGITS
    ities
    0.12
    /local
    0.11
    isation
    0.10
    ised
    0.10
    mente
    0.10
    ized
    0.10
    ity
    0.10
    (local
    0.10
    ization
    0.09
    izedName
    0.09
    Activations Density 0.060%

    No Known Activations