© 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. 50565
    Prev
    Next
    INDEX
    Explanations

    units of measurement (kg, mol, cm, s)

    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
    eningen
    -0.07
    ability
    -0.06
    jos
    -0.06
    uky
    -0.06
    èģĶè½´
    -0.06
    ãģ¯ãĤĵ
    -0.06
    áĭŃ
    -0.06
    âng
    -0.06
    oste
    -0.06
    zio
    -0.06
    POSITIVE LOGITS
    oyer
    0.08
    _SEP
    0.07
    attrs
    0.07
    Ñīем
    0.07
    alus
    0.07
    amu
    0.07
    adu
    0.07
    é«ĺ人
    0.07
    年以ä¸ĭ
    0.07
    室
    0.07
    Activations Density 0.005%

    No Known Activations