© 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. 14000
    Prev
    Next
    INDEX
    Explanations

    letter choice identifier

    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
    _From
    -0.07
    ãĤĴè¿İ
    -0.07
    engu
    -0.07
    ме
    -0.06
    æĶ¾å¿ĥ
    -0.06
    åIJĥä¸į
    -0.06
    æĹłåīį
    -0.06
    etheless
    -0.06
    غÙĬ
    -0.06
    åħħå®ŀèĩªå·±
    -0.06
    POSITIVE LOGITS
    å¢
    0.07
    Įĵ
    0.07
    çѱ
    0.07
    ļa
    0.07
    avis
    0.07
    lease
    0.07
    pecific
    0.07
    該å½ĵ
    0.06
    asaran
    0.06
    uko
    0.06
    Activations Density 0.003%

    No Known Activations