© 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. 62335
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
    ynie
    -0.09
    culus
    -0.09
    ä¸Ĭæŀ¶
    -0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.07
    CLUDE
    -0.07
    goro
    -0.07
    onton
    -0.07
     hél
    -0.07
     trib
    -0.07
    izzes
    -0.07
    POSITIVE LOGITS
    请éĹ®
    0.09
    为ä»Ģä¹Ī说
    0.09
    .Please
    0.08
    为ä»Ģä¹Ī
    0.08
     ìŀĪëĬĶëį°
    0.07
    请å°Ĩ
    0.07
    请
    0.07
    请æĮī
    0.07
    éĥ½è¯´
    0.07
    è¯·åľ¨
    0.07
    Activations Density 0.480%

    No Known Activations