© 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. 3824
    Prev
    Next
    INDEX
    Explanations

    rest, der, other

    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
    rost
    -0.09
    еÑģа
    -0.08
    freund
    -0.08
    ÑĢоди
    -0.08
    еÑīа
    -0.08
    ost
    -0.08
    oop
    -0.07
    osti
    -0.07
    ä»ĭ
    -0.07
    oft
    -0.07
    POSITIVE LOGITS
    æĹłèĻij
    0.08
    <|box_end|>
    0.07
     Choice
    0.07
    oria
    0.06
    æľ¬äººçļĦ
    0.06
    agna
    0.06
    equality
    0.06
    zk
    0.06
    }s
    0.06
    ↵
    0.06
    Activations Density 0.001%

    No Known Activations