© 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. 40390
    Prev
    Next
    INDEX
    Explanations

    particular addition

    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
    ä»İè¿Ļ个
    -0.07
    åħ¬
    -0.07
    ô
    -0.06
    оÑĤÑı
    -0.06
    æļ´éľ²
    -0.06
    ä¸įçŁ¥ä¸įè§īä¸Ń
    -0.06
     Vul
    -0.06
    RefPtr
    -0.06
    注å®ļ
    -0.06
    ustr
    -0.06
    POSITIVE LOGITS
    ITAR
    0.08
    èĭĩ
    0.08
    factory
    0.07
    /feed
    0.07
    leve
    0.07
    yli
    0.07
    onta
    0.07
    reau
    0.07
    Pose
    0.07
    hoe
    0.07
    Activations Density 0.004%

    No Known Activations