© 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. 29922
    Prev
    Next
    INDEX
    Explanations

    highest level or common factor

    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
    erry
    -0.09
    munition
    -0.09
    cter
    -0.09
    ếm
    -0.09
    <|box_end|>
    -0.09
    oust
    -0.08
    ìį¨
    -0.08
    礴
    -0.08
    Ú©ÛĮÙĦ
    -0.08
    erei
    -0.08
    POSITIVE LOGITS
    ablish
    0.10
    ا
    0.09
    ãģªãģĦ
    0.08
     reached
    0.07
    ر
    0.07
    -ever
    0.07
    د
    0.07
     attained
    0.07
    ÑģÑĮ
    0.07
    lal
    0.07
    Activations Density 0.010%

    No Known Activations