© 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. 1711
    Prev
    Next
    INDEX
    Explanations

    какие questions, quelles relations, what all are

    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
    Ø©
    -0.10
    sWith
    -0.09
    ness
    -0.09
    sche
    -0.08
    ation
    -0.08
    ivent
    -0.08
    svar
    -0.08
    sworth
    -0.08
    geb
    -0.08
    scha
    -0.08
    POSITIVE LOGITS
    ãĤĪãģĨãģª
    0.09
    body
    0.08
    ëį°
    0.08
    ever
    0.07
    人èĥ½
    0.07
    uffix
    0.07
    earch
    0.07
    мож
    0.07
    åŃIJæĺ¯
    0.07
    iable
    0.07
    Activations Density 0.001%

    No Known Activations