© 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. 33297
    Prev
    Next
    INDEX
    Explanations

    listing variables

    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
    erton
    -0.08
    лÑıн
    -0.08
    wards
    -0.08
    翼翼
    -0.08
    retien
    -0.08
    aiser
    -0.07
    ëĭ¤ë©´
    -0.07
    åħ·åIJĪ
    -0.07
    Ø©
    -0.07
    elig
    -0.07
    POSITIVE LOGITS
    ized
    0.11
    hood
    0.11
    engeance
    0.10
    erne
    0.10
    oodoo
    0.10
    åĬłæĸ¯
    0.09
    нимание
    0.08
    iously
    0.08
    ocities
    0.08
    mente
    0.08
    Activations Density 0.044%

    No Known Activations