© 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. 40236
    Prev
    Next
    INDEX
    Explanations

    spectral norm, Hellinger distance

    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
     cad
    -0.07
    åŁł
    -0.07
     Nath
    -0.07
    ниÑĩ
    -0.07
    Õ¡Õ°
    -0.07
    vera
    -0.07
    screens
    -0.06
    çļĭ
    -0.06
    صاÙĦات
    -0.06
    ivar
    -0.06
    POSITIVE LOGITS
    ôi
    0.07
    åıĬ以ä¸Ĭ
    0.07
    ngth
    0.07
     Terd
    0.07
    ä¸İä¼Ĺ
    0.07
    èģĺ
    0.07
    vil
    0.06
    ç§ī
    0.06
    èĢĥ
    0.06
    mse
    0.06
    Activations Density 0.001%

    No Known Activations