© 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. 18068
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings

    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
    åĶĶ
    -0.08
    ÙĪاج
    -0.07
    egen
    -0.07
    Parsed
    -0.07
    eron
    -0.07
    ìłĢ
    -0.07
    表达èĥ½åĬĽ
    -0.06
    ä»ĸ家
    -0.06
    Ä
    -0.06
     Enough
    -0.06
    POSITIVE LOGITS
    urrent
    0.08
    è¿ĶåĽŀ顶éĥ¨
    0.08
    heed
    0.07
    çĽĺé¾Ļ
    0.07
    éĴµ
    0.07
    çĻ½å±±
    0.07
    ente
    0.07
    ights
    0.06
    éī¢
    0.06
    нове
    0.06
    Activations Density 0.087%

    No Known Activations