© 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. 45274
    Prev
    Next
    INDEX
    Explanations

    suit, hearts

    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
    evin
    -0.07
    èĬ¸
    -0.07
    åĪ©äºļ
    -0.07
     Aziz
    -0.06
    hely
    -0.06
    ikt
    -0.06
    åħ³äºİ
    -0.06
    ekret
    -0.06
    级
    -0.06
    ä¹ĭ以
    -0.06
    POSITIVE LOGITS
    ç³»çļĦ
    0.08
    ÑĤика
    0.08
    quit
    0.07
    bane
    0.07
    µ
    0.07
     ê³ĦìĹ´
    0.07
    cript
    0.07
    entially
    0.07
    icales
    0.07
    à¤łà¥Ģ
    0.07
    Activations Density 0.003%

    No Known Activations