© 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. 4404
    Prev
    Next
    INDEX
    Explanations

    crystal structures and dimensions

    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
    VML
    -0.08
    amping
    -0.08
    -rated
    -0.08
    aglio
    -0.08
    ostr
    -0.07
    zis
    -0.07
    _locals
    -0.07
    éªļ
    -0.07
    åıįé¦Ī
    -0.07
    Ñģен
    -0.07
    POSITIVE LOGITS
     lattice
    0.07
     vacancy
    0.07
    æĻ¶
    0.07
    apphire
    0.07
     vacancies
    0.07
     Link
    0.07
     linkage
    0.07
    åĽĽæĸ¹
    0.07
    ç´«
    0.07
     link
    0.06
    Activations Density 0.004%

    No Known Activations