© 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. 47113
    Prev
    Next
    INDEX
    Explanations

    end of thanks or questions

    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
    anie
    -0.07
    anty
    -0.07
    rost
    -0.07
    лÑıн
    -0.06
    订
    -0.06
    itis
    -0.06
    })",
    -0.06
                ↵            ↵
    -0.06
    è¿ŀ
    -0.06
    uchy
    -0.06
    POSITIVE LOGITS
    hun
    0.07
    rakt
    0.07
    ommel
    0.07
    omu
    0.07
    _excerpt
    0.07
    .proto
    0.07
    ä¸Ĭ马
    0.07
    _submenu
    0.07
    uha
    0.07
     mote
    0.07
    Activations Density 0.100%

    No Known Activations