© 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. 30677
    Prev
    Next
    INDEX
    Explanations

    following followed by description, video, or relates

    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
    aldas
    -0.07
    ontaine
    -0.07
    eeper
    -0.07
    heimer
    -0.07
    aight
    -0.07
    -ahead
    -0.07
    nière
    -0.07
    quivo
    -0.07
    ooks
    -0.07
     Ø°ÙĬ
    -0.07
    POSITIVE LOGITS
    им
    0.08
    簡稱
    0.07
    æĺ¯å¯¹
    0.07
    itarian
    0.07
    ил
    0.07
    sez
    0.07
    æ§ĺãģª
    0.07
    对åħļ
    0.07
    åįĪ
    0.06
    iver
    0.06
    Activations Density 0.048%

    No Known Activations