© 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. 55976
    Prev
    Next
    INDEX
    Explanations

    consulting

    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
    滦
    -0.08
    å¾ħåĪ°
    -0.07
    /port
    -0.07
    é¢ģ
    -0.07
    éłĴ
    -0.07
    mé
    -0.07
    å°ģ
    -0.07
    å¤©åľ°
    -0.07
    æĬµ
    -0.07
    ANCE
    -0.07
    POSITIVE LOGITS
    ARA
    0.08
     Hatch
    0.07
     Crowley
    0.07
    اج
    0.07
    validators
    0.07
     sto
    0.07
     ------------------------------------------------
    0.06
    >:</
    0.06
    cione
    0.06
    gars
    0.06
    Activations Density 0.066%

    No Known Activations