© 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. 64469
    Prev
    Next
    INDEX
    Explanations

    design, role, oversight, significant

    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
    unic
    -0.08
    ala
    -0.07
    otal
    -0.07
    åĿİ
    -0.07
    ernel
    -0.07
    estal
    -0.07
     anyways
    -0.07
     dial
    -0.06
    åijĬè¯īæĪij们
    -0.06
    éĤ£ä¹ĪçļĦ
    -0.06
    POSITIVE LOGITS
    éĢĢä¼ij
    0.07
    è¯Ħä»·ä½ĵç³»
    0.07
    @app
    0.07
    -disable
    0.07
    Identifier
    0.07
    {/
    0.07
    ç¾½
    0.07
    inters
    0.06
    æīĢæĥ³
    0.06
    ItemAt
    0.06
    Activations Density 0.005%

    No Known Activations