© 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. 50013
    Prev
    Next
    INDEX
    Explanations

    proposal or sharing research

    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
    alde
    -0.08
    سÙĬس
    -0.07
    elah
    -0.07
    æĮijæĪĺåĴĮ
    -0.07
    è§Ĩç½ij
    -0.07
    ë°ĺ
    -0.07
    è¦ģæ±ĤçļĦ
    -0.07
    anz
    -0.07
    riger
    -0.07
    åĬ¿åĬĽ
    -0.06
    POSITIVE LOGITS
    emel
    0.08
    ptos
    0.08
     Seger
    0.08
    akra
    0.07
    סף
    0.07
    udu
    0.07
    gra
    0.07
    eges
    0.07
    ctic
    0.07
    ct
    0.07
    Activations Density 0.001%

    No Known Activations