© 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. 51007
    Prev
    Next
    INDEX
    Explanations

    requesting information or actions

    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
    港澳åı°
    -0.07
    owered
    -0.07
    宿
    -0.07
    ozilla
    -0.07
    !("{}",
    -0.07
    éľ²å¤´
    -0.07
     Adv
    -0.06
    uckland
    -0.06
    CDATA
    -0.06
    ÙĦاÙħ
    -0.06
    POSITIVE LOGITS
    oom
    0.08
     suff
    0.08
    ofile
    0.07
    spo
    0.07
    æĪĸèĢħ缴æİ¥
    0.07
     sens
    0.07
     Suff
    0.07
    æĪĸ缴æİ¥
    0.07
    sens
    0.06
    ops
    0.06
    Activations Density 0.009%

    No Known Activations