© 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. 4339
    Prev
    Next
    INDEX
    Explanations

    stories and accounts

    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
    liness
    -0.09
    serter
    -0.08
    avl
    -0.08
    ward
    -0.08
    hardt
    -0.07
    iness
    -0.07
    manship
    -0.07
    ths
    -0.07
     behalf
    -0.07
    zehn
    -0.07
    POSITIVE LOGITS
     ulang
    0.10
    ìĿ´ìħĺ
    0.10
    atively
    0.10
    angg
    0.09
    ativas
    0.09
    ative
    0.09
    /story
    0.09
    ÙĬØŃØ©
    0.08
    ggio
    0.08
    он
    0.08
    Activations Density 0.012%

    No Known Activations