© 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. 28117
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    onnier
    -0.07
    witter
    -0.07
    uka
    -0.06
    æīįå¹²
    -0.06
    usel
    -0.06
    å°ģ
    -0.06
     (>
    -0.06
    elo
    -0.06
    gota
    -0.06
    uhan
    -0.06
    POSITIVE LOGITS
     lesser
    0.08
    没æľīéĤ£ä¹Ī
    0.08
     simpler
    0.08
    Alt
    0.08
    alt
    0.08
     Less
    0.08
    å°±å¤ŁäºĨ
    0.08
     smaller
    0.07
    uds
    0.07
     thôi
    0.07
    Activations Density 0.081%

    No Known Activations