© 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. 17627
    Prev
    Next
    INDEX
    Explanations

    glm, Madd, crypt, State, dept

    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
    ä»İè½»
    -0.07
     пÑĢедÑĬÑı
    -0.07
    inen
    -0.07
    ardini
    -0.06
    namen
    -0.06
    rello
    -0.06
    ænd
    -0.06
    è¿ĩåħ³
    -0.06
     Carr
    -0.06
    Num
    -0.06
    POSITIVE LOGITS
    orama
    0.08
    è©°
    0.07
    ä½ĵçļĦ
    0.07
    ستÙħ
    0.07
    TRIES
    0.07
    ä½³èĬĤ
    0.06
    æľĽ
    0.06
    大æŀĹ
    0.06
    èĿ
    0.06
    oram
    0.06
    Activations Density 0.006%

    No Known Activations