© 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. 63749
    Prev
    Next
    INDEX
    Explanations

    density, classical, permeability, separating

    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
    á»ĩu
    -0.06
    usta
    -0.06
    æĪŁ
    -0.06
     heter
    -0.06
    äºļçī¹
    -0.06
    eeper
    -0.06
     CO
    -0.06
     kosten
    -0.06
     extrapol
    -0.06
    heter
    -0.06
    POSITIVE LOGITS
     foly
    0.08
    bum
    0.08
    اÙģÛĮ
    0.07
    稿
    0.07
     writable
    0.07
    oseb
    0.07
    mooth
    0.07
    .alloc
    0.07
    portion
    0.07
    åĨĻåŃĹ
    0.07
    Activations Density 0.002%

    No Known Activations