© 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. 33520
    Prev
    Next
    INDEX
    Explanations

    %, followed by comma or number

    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
    beat
    -0.07
    段
    -0.07
     intro
    -0.07
     raz
    -0.06
    è§Ħ
    -0.06
     beyond
    -0.06
    bant
    -0.06
    åĬ¿
    -0.06
    .increment
    -0.06
    intai
    -0.05
    POSITIVE LOGITS
    dden
    0.10
    })",
    0.09
    ccount
    0.09
    жами
    0.08
    icien
    0.08
    iciens
    0.08
    ủng
    0.08
     Zwischen
    0.08
    NavController
    0.07
    izont
    0.07
    Activations Density 0.003%

    No Known Activations