© 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. 51602
    Prev
    Next
    INDEX
    Explanations

    .co articles

    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
    ODO
    -0.08
    acco
    -0.07
    ä¸įåħ¨
    -0.07
    ando
    -0.07
    amac
    -0.06
     kerap
    -0.06
    çݯä¿Ŀå±Ģ
    -0.06
    æ»ĭ润
    -0.06
    ONUS
    -0.06
     Parm
    -0.06
    POSITIVE LOGITS
     caut
    0.09
    ../../../../
    0.08
    å¸ĮæľĽèĥ½å¤Łå¸®åĬ©
    0.08
    TERN
    0.08
    ubat
    0.07
    unki
    0.07
    ÑĤÑĮе
    0.07
    åIJŃ
    0.07
    istrator
    0.07
    žen
    0.07
    Activations Density 0.003%

    No Known Activations