© 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. 18150
    Prev
    Next
    INDEX
    Explanations

    mine

    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
     Bergen
    -0.07
     cru
    -0.06
    ä»
    -0.06
    ä¸įå±ij
    -0.06
     fou
    -0.06
     pert
    -0.06
    -0.06
    íķ¨
    -0.06
     psych
    -0.06
    ο
    -0.06
    POSITIVE LOGITS
    ä¸İåħ±
    0.09
    sonian
    0.09
    hawk
    0.09
    åij³çļĦ
    0.09
    viel
    0.08
    zuk
    0.08
    .roll
    0.08
    riors
    0.08
    raid
    0.08
     tảng
    0.08
    Activations Density 0.005%

    No Known Activations