© 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. 63549
    Prev
    Next
    INDEX
    Explanations

    via, mittels, tramite, mithilfe, mediante

    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
    æĽľ
    -0.06
    ÑıÑħ
    -0.06
    åł¡
    -0.06
    éĿĴè¡£
    -0.06
    YA
    -0.06
     teng
    -0.06
    ozo
    -0.06
     пÑĢиÑĪ
    -0.06
     Tym
    -0.06
    å¿ĥæĥĬ
    -0.06
    POSITIVE LOGITS
     via
    0.23
    via
    0.21
     mittels
    0.20
     Via
    0.19
    Via
    0.18
     поÑģÑĢедÑģÑĤвом
    0.17
     tramite
    0.17
    åı¯éĢļè¿ĩ
    0.16
     mithilfe
    0.16
     mediante
    0.16
    Activations Density 1.808%

    No Known Activations