© 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. 4072
    Prev
    Next
    INDEX
    Explanations

    gain values

    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
    vlak
    -0.07
    kana
    -0.07
    arczy
    -0.07
    èĩªéĹŃ
    -0.06
    iven
    -0.06
    lint
    -0.06
    èĤĩ
    -0.06
    rzy
    -0.06
    benen
    -0.06
    æ°Ľ
    -0.06
    POSITIVE LOGITS
     пон
    0.08
    obra
    0.07
    鲫
    0.07
    åį¸è½½
    0.07
    acle
    0.07
    åį¸
    0.07
    esan
    0.07
    BASH
    0.07
    ÑģмоÑĤÑĢÑı
    0.07
    伯çī¹
    0.07
    Activations Density 0.006%

    No Known Activations