© 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. 22918
    Prev
    Next
    INDEX
    Explanations

    example choice language process length matrix chronological parameter

    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
    梨èĬ±
    -0.07
    imore
    -0.06
    à¯Ĩ
    -0.06
    áĥĶáĥĹ
    -0.06
    åĩĮäºij
    -0.06
    ICI
    -0.06
    linger
    -0.06
     capt
    -0.06
     InputStreamReader
    -0.06
    าศ
    -0.06
    POSITIVE LOGITS
    agal
    0.08
    лаÑĤÑĭ
    0.08
    碰碰
    0.08
     Pruitt
    0.07
    inho
    0.07
    .enumer
    0.07
    mitt
    0.07
    daw
    0.07
    大人çļĦ
    0.07
    tod
    0.07
    Activations Density 0.051%

    No Known Activations