© 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. 12278
    Prev
    Next
    INDEX
    Explanations

    references and citations

    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
    ëijĺ
    -0.08
    erra
    -0.07
    èĭ«
    -0.07
    rhein
    -0.07
    iose
    -0.06
    ascal
    -0.06
    urit
    -0.06
    ä¹ĭçĪ¶
    -0.06
    ois
    -0.06
    iere
    -0.06
    POSITIVE LOGITS
    ;amp
    0.07
    _atts
    0.06
     tur
    0.06
    大ä¼Ļ
    0.06
     Zuk
    0.06
    Jvm
    0.06
    estring
    0.06
     inv
    0.06
    çĤ¹åĩ»éĺħ读åİŁæĸĩ
    0.06
    à¤Ĥध
    0.06
    Activations Density 0.017%

    No Known Activations