© 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. 30965
    Prev
    Next
    INDEX
    Explanations

    contributes to effects

    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
    adari
    -0.07
    ash
    -0.07
    ár
    -0.06
    à¦ŀà§įà¦ľ
    -0.06
    query
    -0.06
    ungalow
    -0.06
     Lohn
    -0.06
    ee
    -0.06
    ise
    -0.06
     Administrasi
    -0.06
    POSITIVE LOGITS
     صاØŃ
    0.09
    éĻ¶åĨ¶
    0.09
    ç¼Ń
    0.07
    解åĨ³å®ŀéĻħ
    0.07
    plr
    0.07
    htable
    0.07
    å¾Īå¤ļä¸ľè¥¿
    0.07
    大ä¸ĸçķĮ
    0.07
    éĢłç¦ı
    0.07
    wod
    0.07
    Activations Density 0.770%

    No Known Activations