© 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. 48076
    Prev
    Next
    INDEX
    Explanations

    incremental complexity or transitions

    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
    amai
    -0.08
    elay
    -0.08
    ADIO
    -0.08
    ipro
    -0.08
     Raised
    -0.08
    aoke
    -0.07
    etermine
    -0.07
    mtime
    -0.07
    ży
    -0.07
     redirects
    -0.07
    POSITIVE LOGITS
     initially
    0.08
    éĢIJ
    0.08
    isson
    0.07
    à¹Ģà¸Ħ
    0.07
    atre
    0.07
     transition
    0.07
    éĢIJæŃ¥
    0.07
    Transition
    0.07
    åĪĿå§ĭ
    0.07
    èĪįä¸įå¾Ĺ
    0.07
    Activations Density 0.005%

    No Known Activations