© 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. 49313
    Prev
    Next
    INDEX
    Explanations

    stabilize, stability, ability

    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
    avanaugh
    -0.08
    ä¸įåĪ°çļĦ
    -0.08
    िता
    -0.08
    quel
    -0.08
     dại
    -0.08
    หà¸Ļà¹īาà¸Ļีà¹ī
    -0.08
    áĥķáĥľ
    -0.07
    ptions
    -0.07
    elsen
    -0.07
    isel
    -0.07
    POSITIVE LOGITS
    andalone
    0.09
    ÑĤ
    0.09
     vững
    0.09
    æĢ§çļĦ
    0.08
    èµ·è§ģ
    0.08
    uttgart
    0.08
    opedia
    0.08
    uffers
    0.08
    uart
    0.08
    coins
    0.07
    Activations Density 0.036%

    No Known Activations