© 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. 56361
    Prev
    Next
    INDEX
    Explanations

    psi, Psi, PSI

    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
    ¸
    -0.10
    [href
    -0.09
    eness
    -0.08
    ämp
    -0.08
    esia
    -0.08
     swath
    -0.08
    èĴĻå¾·
    -0.08
    ossi
    -0.08
    ipay
    -0.08
    hetto
    -0.08
    POSITIVE LOGITS
    apiro
    0.08
    бÑĥдÑĮÑĤе
    0.07
    ysical
    0.07
    midt
    0.07
    pered
    0.07
    neider
    0.07
    کارÛĮ
    0.07
    thetic
    0.07
    بÙĥØ©
    0.07
    schede
    0.07
    Activations Density 0.009%

    No Known Activations