© 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. 57660
    Prev
    Next
    INDEX
    Explanations

    H, Theta, filters, ID, input, output

    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
    olong
    -0.07
    æĿ¥çĶµ
    -0.07
     le
    -0.06
    æŁĴ
    -0.06
    èĩĬ
    -0.06
    xid
    -0.06
    è¶Ł
    -0.06
     ab
    -0.06
    ç²Ĺæļ´
    -0.06
    chu
    -0.06
    POSITIVE LOGITS
    mime
    0.08
    åĹ½
    0.08
    basePath
    0.08
    =output
    0.08
    ¬¸
    0.08
    _allocated
    0.08
    stö
    0.08
    funktionen
    0.08
    getResponse
    0.07
     outputPath
    0.07
    Activations Density 0.006%

    No Known Activations