© 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. 51145
    Prev
    Next
    INDEX
    Explanations

    ECT email suffix

    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
    #=
    -0.11
    -0.08
    导读
    -0.07
    мом
    -0.07
    wend
    -0.07
     ÙĦاØŃ
    -0.07
    aki
    -0.07
    ĭ
    -0.07
    icable
    -0.07
    åĩºåİ»çļĦ
    -0.07
    POSITIVE LOGITS
    chow
    0.07
    anson
    0.07
    AndPassword
    0.06
    åĪĿ
    0.06
    .bz
    0.06
    çıĪ
    0.06
    æĺ¯
    0.06
    asco
    0.06
    RefCount
    0.06
    aira
    0.06
    Activations Density 0.044%

    No Known Activations