© 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. 48225
    Prev
    Next
    INDEX
    Explanations

    technically, Lies, namely

    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
    æ¦Ķ
    -0.08
    åĴĮå¹³
    -0.07
    igan
    -0.07
    IDAS
    -0.07
    akis
    -0.07
    èĻ«
    -0.06
     Wor
    -0.06
    drag
    -0.06
    约翰éĢĬ
    -0.06
    å°±æĺ¯ä¸Ģ
    -0.06
    POSITIVE LOGITS
    estero
    0.08
    eel
    0.08
    -origin
    0.07
    Cir
    0.07
    ially
    0.07
    huis
    0.07
    atetime
    0.07
    -exp
    0.07
    循
    0.07
    æĪ·æĪ·
    0.07
    Activations Density 0.004%

    No Known Activations