© 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. 38454
    Prev
    Next
    INDEX
    Explanations

    copyright text, LWJGL, ref markdown

    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
     “
    -0.08
    ô
    -0.07
    纵
    -0.06
    asty
    -0.06
    ↵
    -0.06
     powered
    -0.06
    纵åIJij
    -0.06
    ly
    -0.06
     vo
    -0.06
     familiar
    -0.06
    POSITIVE LOGITS
    anke
    0.09
    okok
    0.09
    è¿Ļ件äºĭæĥħ
    0.08
    लि
    0.08
    porno
    0.08
    goed
    0.08
    Ñħай
    0.08
    åħ¨å·ŀ
    0.08
    nö
    0.08
    воÑĢ
    0.08
    Activations Density 0.001%

    No Known Activations