© 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. 21033
    Prev
    Next
    INDEX
    Explanations

    broadband services, regulation, collaborations, mapping

    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
    ulik
    -0.08
    ignon
    -0.07
    ç¨
    -0.06
    umpf
    -0.06
     Toe
    -0.06
     heav
    -0.06
    agle
    -0.06
    alon
    -0.06
    UL
    -0.06
     Brothers
    -0.06
    POSITIVE LOGITS
    imuth
    0.08
    å°±æĺ¯æĮĩ
    0.08
    项è§Ħå®ļ
    0.07
    å°±æĺ¯è¯´
    0.07
    qs
    0.07
    lap
    0.07
    hluk
    0.07
    åįģéĩĮ
    0.07
    ene
    0.07
    оÑĢÑĤа
    0.07
    Activations Density 0.027%

    No Known Activations