© 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. 12609
    Prev
    Next
    INDEX
    Explanations

    option variable

    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
    äºĭ
    -0.06
    被æĬĵ
    -0.06
    qd
    -0.06
    ä½łåij¢
    -0.05
    Õ¸ÖĢ
    -0.05
    åħħ满
    -0.05
     pig
    -0.05
    ordo
    -0.05
    ude
    -0.05
    inue
    -0.05
    POSITIVE LOGITS
    idel
    0.09
    çļĦ人æ°ij
    0.08
    comings
    0.08
    çļĦåĽ½å®¶
    0.08
    aar
    0.08
    à¹ģย
    0.08
    人å±ħ
    0.07
    ÑĤам
    0.07
    vice
    0.07
    åħĭéĩĮ
    0.07
    Activations Density 0.001%

    No Known Activations