© 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. 13148
    Prev
    Next
    INDEX
    Explanations

    additional assumptions

    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
    cion
    -0.07
    cki
    -0.07
     REPRESENT
    -0.07
    æĥ¹
    -0.07
    hart
    -0.07
    miet
    -0.07
    olicit
    -0.07
    паÑĤи
    -0.07
    heet
    -0.07
    verg
    -0.07
    POSITIVE LOGITS
    æīįèĥ½ä½¿
    0.08
    åģĩ设
    0.07
    ox
    0.07
     assumptions
    0.07
    idence
    0.07
    èĥ½å¤Łä½¿
    0.07
    为äºĨ使
    0.07
     undercover
    0.06
    .assert
    0.06
    OX
    0.06
    Activations Density 0.001%

    No Known Activations