© 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. 25018
    Prev
    Next
    INDEX
    Explanations

    bowl, card, iPod

    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
    alc
    -0.08
    n
    -0.07
    áĢ²
    -0.07
    nal
    -0.06
    ae
    -0.06
    ãģķãģĦ
    -0.06
    aim
    -0.06
    ke
    -0.06
    essa
    -0.06
    æķĽ
    -0.06
    POSITIVE LOGITS
    áva
    0.09
    ihar
    0.08
    ingar
    0.08
    æĹ¥çĶŁ
    0.07
    akov
    0.07
    หมายà¸Ħวาม
    0.07
    涯
    0.07
    mara
    0.07
    -condition
    0.07
    eluk
    0.07
    Activations Density 0.855%

    No Known Activations