© 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. 56428
    Prev
    Next
    INDEX
    Explanations

    after function or punctuation

    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
    zaÅĦ
    -0.07
    åĩ«
    -0.07
    èŀĥ
    -0.07
    quist
    -0.07
    oze
    -0.06
    è¿Ļç§įè¡Į为
    -0.06
    itäts
    -0.06
    UAR
    -0.06
     classified
    -0.06
    æĭĮ
    -0.06
    POSITIVE LOGITS
    ickey
    0.08
    fsp
    0.07
     اÙĦÙħتر
    0.07
     gespi
    0.07
    unt
    0.07
    ä½İè¿·
    0.07
    éĦĻ
    0.07
    ä¸½å¨ľ
    0.06
    azel
    0.06
     Vinci
    0.06
    Activations Density 0.220%

    No Known Activations