© 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. 22527
    Prev
    Next
    INDEX
    Explanations

    before `public class`

    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
    -0.09
    wards
    -0.09
    erma
    -0.08
    oriously
    -0.08
    sgi
    -0.08
    ิà¸Ī
    -0.08
    esign
    -0.08
    icona
    -0.08
    iden
    -0.08
    ened
    -0.07
    POSITIVE LOGITS
    ishing
    0.08
    ding
    0.07
    ึà¸ģ
    0.07
    ancy
    0.07
    usc
    0.07
    ä¸Ģå¤ķ
    0.07
    ested
    0.07
    antly
    0.07
    ³
    0.06
    bildungs
    0.06
    Activations Density 0.145%

    No Known Activations