© 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. 45926
    Prev
    Next
    INDEX
    Explanations

    minimum spanning, principal frame, immune mouse, class reunion, eruption cyst

    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
    íĻĶê°Ģ
    -0.07
    íĻĶ를
    -0.07
    ahren
    -0.07
    gede
    -0.06
    íĻĶëĬĶ
    -0.06
    íĻĶë¡ľ
    -0.06
    íĻĶìĻĢ
    -0.06
    indo
    -0.06
    ondas
    -0.06
    æľīä¸Ń
    -0.06
    POSITIVE LOGITS
    acci
    0.08
    åĬ¡
    0.08
    ims
    0.07
    /general
    0.07
    poi
    0.07
    åĭĻ
    0.07
    è¿Ļä¹Īå¤ļçļĦ
    0.07
    igh
    0.07
    æĶ¹å»º
    0.07
    Unload
    0.07
    Activations Density 0.026%

    No Known Activations