© 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. 28818
    Prev
    Next
    INDEX
    Explanations

    words before names of places or people

    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
    infeld
    -0.07
    å§Ķ
    -0.07
    Blob
    -0.07
    è¿Ľä¸ĢæŃ¥åĬłå¼º
    -0.07
    atti
    -0.07
    dain
    -0.07
    .enums
    -0.07
    à¹Ħà¸Ĭ
    -0.07
    adini
    -0.07
    ergy
    -0.07
    POSITIVE LOGITS
    rot
    0.07
    oc
    0.07
    ect
    0.07
    okal
    0.06
    LEX
    0.06
    öm
    0.06
    ok
    0.06
    occa
    0.06
    æµıè§Ī次æķ°
    0.06
    人类社ä¼ļ
    0.06
    Activations Density 0.618%

    No Known Activations