© 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. 22573
    Prev
    Next
    INDEX
    Explanations

    letter-number combinations

    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
    rones
    -0.08
    ienda
    -0.08
    обо
    -0.07
     Granny
    -0.07
    esco
    -0.07
    iers
    -0.07
    croft
    -0.07
    æĪ¶
    -0.07
    ierer
    -0.07
    roat
    -0.07
    POSITIVE LOGITS
    aks
    0.07
    ç§ij主任
    0.07
    çĻ½å±±
    0.07
    TML
    0.07
    æĬĬæīĭ
    0.06
     sal
    0.06
     sob
    0.06
    è¶Ĭèµ°
    0.06
    è¶Ĭ
    0.06
    æĪĴ
    0.06
    Activations Density 0.002%

    No Known Activations