© 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. 8646
    Prev
    Next
    INDEX
    Explanations

    EACH other

    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
     Manuel
    -0.06
    orique
    -0.06
    _lvl
    -0.06
    hares
    -0.06
    aus
    -0.06
    èģļåIJĪçī©
    -0.06
    ique
    -0.06
    mán
    -0.06
    山寨
    -0.06
    üll
    -0.06
    POSITIVE LOGITS
    opa
    0.08
     clearTimeout
    0.07
    æīįèĥ½ä½¿
    0.07
    æīįèĥ½è®©
    0.07
    urope
    0.07
    ork
    0.07
    ntag
    0.07
    ä¸įå¼ĥ
    0.07
    ä¸Ģ件äºĭæĥħ
    0.07
    交åĬŀçļĦåħ¶ä»ĸ
    0.07
    Activations Density 0.001%

    No Known Activations