© 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. 32486
    Prev
    Next
    INDEX
    Explanations

    relatively + comparative

    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
    ible
    -0.09
    aum
    -0.09
    onas
    -0.09
    yder
    -0.08
    åĮ»ç§ij大åѦéĻĦå±ŀ
    -0.08
    fulness
    -0.08
    einander
    -0.08
    вален
    -0.08
    ertos
    -0.08
    amá
    -0.08
    POSITIVE LOGITS
    -than
    0.12
    _than
    0.10
    ly
    0.09
     than
    0.09
    ĥ
    0.08
    zelfde
    0.08
    ģ
    0.08
    ลฯ
    0.08
    than
    0.07
    ĵ
    0.07
    Activations Density 0.001%

    No Known Activations