© 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. 38166
    Prev
    Next
    INDEX
    Explanations

    ivoli, Boston Marathon bombing

    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
    åĨħå¿ĥæ·±å¤Ħ
    -0.06
    ×ķתר
    -0.06
    lington
    -0.06
    বà§įয
    -0.06
    aling
    -0.06
    лÑıÑĤ
    -0.06
    ä¸Ģè¯ķ
    -0.06
    _sep
    -0.06
     schlimm
    -0.06
    翼翼
    -0.06
    POSITIVE LOGITS
    falt
    0.07
    epe
    0.07
    rieb
    0.07
    .deb
    0.07
    rimon
    0.07
    æĥħæĦ¿
    0.07
     Bombe
    0.07
    å¸ĥéĩĮ
    0.06
    Äįaj
    0.06
    iteral
    0.06
    Activations Density 0.002%

    No Known Activations