© 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. 23884
    Prev
    Next
    INDEX
    Explanations

    via using mittels 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
    æĪijè¦ģè¯Ħ论
    -0.07
    arine
    -0.07
    ilie
    -0.07
    allah
    -0.07
    æĿī
    -0.07
    teo
    -0.06
    ptos
    -0.06
    _ABI
    -0.06
    _wr
    -0.06
    ç§Ģ
    -0.06
    POSITIVE LOGITS
     via
    0.25
    via
    0.20
     mittels
    0.20
     using
    0.20
     bằng
    0.18
     поÑģÑĢедÑģÑĤвом
    0.18
    çĶ¨
    0.18
    éĥ½æĺ¯çĶ¨
    0.17
     Via
    0.17
     mediante
    0.17
    Activations Density 0.927%

    No Known Activations