© 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. 43546
    Prev
    Next
    INDEX
    Explanations

    carbon and related chemical terms

    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
    éľĨ
    -0.08
    åħĭåħ°
    -0.08
    ettor
    -0.08
    izont
    -0.08
    æģĻ
    -0.07
    agner
    -0.07
    orza
    -0.07
    ToMany
    -0.07
    reak
    -0.07
     Bref
    -0.07
    POSITIVE LOGITS
    碳
    0.10
    Carbon
    0.10
    carbon
    0.10
     carbon
    0.10
    arbon
    0.09
     Carbon
    0.09
    aceous
    0.09
    nja
    0.08
     carbone
    0.08
    à¸ģลà¹īา
    0.08
    Activations Density 0.018%

    No Known Activations