© 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. 63677
    Prev
    Next
    INDEX
    Explanations

    secure bra, energy, certain

    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
    -0.08
    /to
    -0.08
    uel
    -0.08
    ack
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    quist
    -0.08
    ÅĽcie
    -0.07
    uxtap
    -0.07
    ancock
    -0.07
    ictures
    -0.07
    POSITIVE LOGITS
    OrCreate
    0.10
    ly
    0.10
    æĹłè¯¯
    0.09
    ainty
    0.09
    æĹłçĸij
    0.09
    çĶ³åijĬ
    0.09
    AndGet
    0.09
    ие
    0.08
     chắn
    0.08
    ledge
    0.08
    Activations Density 0.002%

    No Known Activations