© 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. 12856
    Prev
    Next
    INDEX
    Explanations

    alternative to

    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
    å®ŀå¤Ħ
    -0.09
    dach
    -0.08
     ulang
    -0.08
    ings
    -0.08
    над
    -0.08
    -ahead
    -0.08
    inkan
    -0.08
    eviÄĩ
    -0.08
    æĸ°åĮº
    -0.07
    INGS
    -0.07
    POSITIVE LOGITS
    æĢ§çļĦ
    0.08
    /add
    0.08
    fois
    0.08
    wis
    0.08
     Weise
    0.07
    åĴĮæĸ°
    0.07
    idades
    0.07
    odox
    0.07
    -looking
    0.07
    ìĹĨìĿ´
    0.07
    Activations Density 0.024%

    No Known Activations