© 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. 56424
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    endr
    -0.07
    æķĻ
    -0.07
    klus
    -0.06
    ells
    -0.06
     amen
    -0.06
    IFE
    -0.06
    ÑīиÑĤе
    -0.06
    acea
    -0.06
    ptic
    -0.06
    à§ĩস
    -0.06
    POSITIVE LOGITS
    èijµ
    0.08
    ascar
    0.08
    itzer
    0.08
    åIJĮä¸Ĭ
    0.08
    åºĹéķĩ
    0.07
    åįĥåįĥ
    0.07
    ä¸ĭæīĭ
    0.07
     Bass
    0.07
    ESCO
    0.07
    常æľī
    0.07
    Activations Density 0.010%

    No Known Activations