© 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. 40706
    Prev
    Next
    INDEX
    Explanations

    code fragments using punctuation

    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
    ement
    -0.07
    èħ¾
    -0.07
    iname
    -0.07
     Moro
    -0.07
    èĦı
    -0.07
    aci
    -0.07
    Enumerator
    -0.07
    IPT
    -0.07
    æİĪ
    -0.07
    vanized
    -0.06
    POSITIVE LOGITS
    åı¦å¤ĸä¸Ģ个
    0.08
    ä¸įçľĭ
    0.07
    anita
    0.07
    alse
    0.06
    ĴĪ
    0.06
    Ĩµ
    0.06
    udos
    0.06
     whom
    0.06
    åĥ¹
    0.06
    pira
    0.06
    Activations Density 0.002%

    No Known Activations